7daf3b2 · crush · git.iko.soy

git.iko.soy/crush

on main help sign in

fix(tests): regenerate tests and skip some

7daf3b2kujtimiihoxha1 year ago

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yaml+48−48

compare with main

unifiedsplit

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,56 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_0134NcQsuCWiH9G2f1pFdbjd","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01Qns4bhGsHTJigK4SYz1ND9","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Bash File"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Bash File"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Creation"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Creation"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" with"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Comman"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Hello Message"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d"} }

48 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

49+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} }

52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} }

54 event: message_stop

55− data: {"type":"message_stop" }

55+ data: {"type":"message_stop" }

57 headers:

58 Content-Type:

59 - text/event-stream; charset=utf-8

60 status: 200 OK

61 code: 200

62− duration: 580.862ms

62+ duration: 861.204083ms

63- id: 1

64 request:

65 proto: HTTP/1.1

66 proto_major: 1

67 proto_minor: 1

68− content_length: 32080

68+ content_length: 31156

69 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

72 Accept:

73 - application/json

74 Content-Type:

75 - application/json

76 User-Agent:

77− - Anthropic/Go 1.12.0

77+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

79 method: POST

80 response:

@@ -84,89 +84,92 @@ interactions:

84 content_length: -1

85 body: |+

86 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_014HBZ4z2bf13yA4JhmVnxwF","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1807,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LD78rchPCB51cQpGurtYoJ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1716,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

89 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01YBoqWcXiuoc1fZf4muKFXn","name":"bash","input":{}} }

90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01FWkL4iH4i6owfcGsk4Z29y","name":"bash","input":{}} }

92 event: content_block_delta

93 data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}}

95 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"com"} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"com"}}

97+

98+ event: content_block_delta

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mand\": \"ec"} }

100

98 event: content_block_delta

101 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mand"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ho 'hello "} }

100

103

101 event: content_block_delta

104 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"echo 'h"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"bash' > te"} }

103

106

104 event: content_block_delta

107 event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ello bas"} }

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"st"} }

106

109

107 event: content_block_delta

110 event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h'"} }

111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".txt\""} }

109

112

110 event: content_block_delta

113 event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" > te"} }

114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"d"} }

112

115

113 event: content_block_delta

116 event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"st.txt\""} }

117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"es"} }

115

118

116 event: content_block_delta

119 event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"descript"} }

120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"cription\":"} }

118

121

119 event: content_block_delta

122 event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ion\": \"C"} }

123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"Create "} }

121

124

122 event: content_block_delta

125 event: content_block_delta

123− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"reat"} }

126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"test.t"} }

124

127

125 event: content_block_delta

128 event: content_block_delta

126− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e tes"} }

129+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"xt wit"} }

127

130

128 event: content_block_delta

131 event: content_block_delta

129− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t.txt with"} }

132+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h con"} }

130

133

131 event: content_block_delta

134 event: content_block_delta

132− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" content 'h"} }

135+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tent 'h"} }

133

136

134 event: content_block_delta

137 event: content_block_delta

135− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"el"} }

138+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ello bash'"} }

136

139

137 event: content_block_delta

140 event: content_block_delta

138− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo bash'\"}"} }

141+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

139

142

140 event: content_block_stop

143 event: content_block_stop

141− data: {"type":"content_block_stop","index":0 }

144+ data: {"type":"content_block_stop","index":0}

142

145

143 event: message_delta

146 event: message_delta

144− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"output_tokens":87} }

147+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"output_tokens":87} }

145

148

146 event: message_stop

149 event: message_stop

147− data: {"type":"message_stop" }

150+ data: {"type":"message_stop" }

148

151

149 headers:

152 headers:

150 Content-Type:

153 Content-Type:

151 - text/event-stream; charset=utf-8

154 - text/event-stream; charset=utf-8

152 status: 200 OK

155 status: 200 OK

153 code: 200

156 code: 200

154− duration: 2.250892459s

157+ duration: 2.2726605s

155- id: 2

158- id: 2

156 request:

159 request:

157 proto: HTTP/1.1

160 proto: HTTP/1.1

158 proto_major: 1

161 proto_major: 1

159 proto_minor: 1

162 proto_minor: 1

160− content_length: 32481

163+ content_length: 31557

161 host: ""

164 host: ""

162− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01YBoqWcXiuoc1fZf4muKFXn\",\"input\":{\"command\":\"echo 'hello bash' \\u003e test.txt\",\"description\":\"Create test.txt with content 'hello bash'\"},\"name\":\"bash\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01YBoqWcXiuoc1fZf4muKFXn\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"no output\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

165+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01FWkL4iH4i6owfcGsk4Z29y\",\"input\":{\"command\":\"echo 'hello bash' \\u003e test.txt\",\"description\":\"Create test.txt with content 'hello bash'\"},\"name\":\"bash\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01FWkL4iH4i6owfcGsk4Z29y\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"no output\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

163 headers:

166 headers:

164 Accept:

167 Accept:

165 - application/json

168 - application/json

166 Content-Type:

169 Content-Type:

167 - application/json

170 - application/json

168 User-Agent:

171 User-Agent:

169− - Anthropic/Go 1.12.0

172+ - Anthropic/Go 1.14.0

170 url: https://api.anthropic.com/v1/messages

173 url: https://api.anthropic.com/v1/messages

171 method: POST

174 method: POST

172 response:

175 response:

@@ -176,29 +179,26 @@ interactions:

176 content_length: -1

179 content_length: -1

177 body: |+

180 body: |+

178 event: message_start

181 event: message_start

179− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01VhFdZK9M9rh9iPzGkdoG1R","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":99,"cache_read_input_tokens":8660,"cache_creation":{"ephemeral_5m_input_tokens":99,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

182+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01GwkeutdSvaJFY2dhVh6Znj","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":99,"cache_read_input_tokens":8568,"cache_creation":{"ephemeral_5m_input_tokens":99,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

180

183

181 event: content_block_start

184 event: content_block_start

182− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

185+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

183−

184− event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"File"} }

186

187 event: content_block_delta

188− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" created successfully."} }

188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

189

190 event: content_block_stop

191− data: {"type":"content_block_stop","index":0 }

191+ data: {"type":"content_block_stop","index":0 }

192

193 event: message_delta

194− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":99,"cache_read_input_tokens":8660,"output_tokens":7} }

194+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":99,"cache_read_input_tokens":8568,"output_tokens":4} }

195

196 event: message_stop

197− data: {"type":"message_stop" }

197+ data: {"type":"message_stop" }

198

199 headers:

200 Content-Type:

201 - text/event-stream; charset=utf-8

202 status: 200 OK

203 code: 200

204− duration: 2.466855833s

204+ duration: 2.283322125s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yaml+48−57

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,56 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01HgEdLNNxYjaZP4qdjC1kgA","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":151,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01YE4hcHSKgePa9XeDaDHHc3","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":151,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Downloa"}}

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Downloa"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d robots"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Robots.txt from HTTP"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".txt from http"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"B"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"bin.org"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"in"} }

48 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

49+ data: {"type":"content_block_stop","index":0}

51 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":151,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":151,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

54 event: message_stop

55− data: {"type":"message_stop" }

55+ data: {"type":"message_stop" }

57 headers:

58 Content-Type:

59 - text/event-stream; charset=utf-8

60 status: 200 OK

61 code: 200

62− duration: 538.064375ms

62+ duration: 661.353334ms

63- id: 1

64 request:

65 proto: HTTP/1.1

66 proto_major: 1

67 proto_minor: 1

68− content_length: 32097

68+ content_length: 31173

69 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

72 Accept:

73 - application/json

74 Content-Type:

75 - application/json

76 User-Agent:

77− - Anthropic/Go 1.12.0

77+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

79 method: POST

80 response:

@@ -84,56 +84,62 @@ interactions:

84 content_length: -1

85 body: |+

86 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_019KcWmqSk79v6LJf1bza4q3","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1811,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1811,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01WRwMaD88XudHFovT9JisXa","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1720,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1720,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

89 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01TQRnNYg7te6aMms1MBRHL8","name":"download","input":{}} }

90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_011NZBWVRQ4Xh8eyVoJ3nkgq","name":"download","input":{}} }

91+

92+ event: content_block_delta

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

94+

95+ event: content_block_delta

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"ur"} }

92 event: content_block_delta

98 event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"l\": \"h"} }

100

95 event: content_block_delta

101 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"u"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tt"} }

103

98 event: content_block_delta

104 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rl\": \"https:"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ps://httpbi"} }

100

106

101 event: content_block_delta

107 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"//httpbin."}}

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n.org/robots"} }

103

109

104 event: content_block_delta

110 event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"org/robots."} }

111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".txt"} }

106

112

107 event: content_block_delta

113 event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"txt\""} }

114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\""} }

109

115

110 event: content_block_delta

116 event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"file_pat"} }

117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"file_path"} }

112

118

113 event: content_block_delta

119 event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"rob"} }

120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"rob"} }

115

121

116 event: content_block_delta

122 event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ots.tx"} }

123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ot"} }

118

124

119 event: content_block_delta

125 event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t\"}"} }

126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"s.txt\"}"} }

121

127

122 event: content_block_stop

128 event: content_block_stop

123− data: {"type":"content_block_stop","index":0 }

129+ data: {"type":"content_block_stop","index":0 }

124

130

125 event: message_delta

131 event: message_delta

126− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1811,"cache_read_input_tokens":6853,"output_tokens":81} }

132+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1720,"cache_read_input_tokens":6852,"output_tokens":81} }

127

133

128 event: message_stop

134 event: message_stop

129− data: {"type":"message_stop" }

135+ data: {"type":"message_stop" }

130

136

131 headers:

137 headers:

132 Content-Type:

138 Content-Type:

133 - text/event-stream; charset=utf-8

139 - text/event-stream; charset=utf-8

134 status: 200 OK

140 status: 200 OK

135 code: 200

141 code: 200

136− duration: 2.481377833s

142+ duration: 2.24605475s

137- id: 2

143- id: 2

138 request:

144 request:

139 proto: HTTP/1.1

145 proto: HTTP/1.1

@@ -159,22 +165,22 @@ interactions:

159 - text/plain

165 - text/plain

160 status: 200 OK

166 status: 200 OK

161 code: 200

167 code: 200

162− duration: 1.07370375s

168+ duration: 1.51167225s

163- id: 3

169- id: 3

164 request:

170 request:

165 proto: HTTP/1.1

171 proto: HTTP/1.1

166 proto_major: 1

172 proto_major: 1

167 proto_minor: 1

173 proto_minor: 1

168− content_length: 32588

174+ content_length: 31664

169 host: ""

175 host: ""

170− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01TQRnNYg7te6aMms1MBRHL8\",\"input\":{\"file_path\":\"robots.txt\",\"url\":\"https://httpbin.org/robots.txt\"},\"name\":\"download\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01TQRnNYg7te6aMms1MBRHL8\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/robots.txt (Content-Type: text/plain)\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

176+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_011NZBWVRQ4Xh8eyVoJ3nkgq\",\"input\":{\"file_path\":\"robots.txt\",\"url\":\"https://httpbin.org/robots.txt\"},\"name\":\"download\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_011NZBWVRQ4Xh8eyVoJ3nkgq\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/robots.txt (Content-Type: text/plain)\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

171 headers:

177 headers:

172 Accept:

178 Accept:

173 - application/json

179 - application/json

174 Content-Type:

180 Content-Type:

175 - application/json

181 - application/json

176 User-Agent:

182 User-Agent:

177− - Anthropic/Go 1.12.0

183+ - Anthropic/Go 1.14.0

178 url: https://api.anthropic.com/v1/messages

184 url: https://api.anthropic.com/v1/messages

179 method: POST

185 method: POST

180 response:

186 response:

@@ -184,44 +190,29 @@ interactions:

184 content_length: -1

190 content_length: -1

185 body: |+

191 body: |+

186 event: message_start

192 event: message_start

187− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01HaRYTipxH4buqTj1ojHLri","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":132,"cache_read_input_tokens":8664,"cache_creation":{"ephemeral_5m_input_tokens":132,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

193+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01QSqoGqpguj55cNYgNJv5yZ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":132,"cache_read_input_tokens":8572,"cache_creation":{"ephemeral_5m_input_tokens":132,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

188

194

189 event: content_block_start

195 event: content_block_start

190− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

196+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

191−

192− event: content_block_delta

193− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

194

197

195 event: content_block_delta

198 event: content_block_delta

196− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":". Downloaded 30 bytes to `"} }

199+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Downloade"} }

197−

198− event: ping

199− data: {"type": "ping"}

200

201 event: content_block_delta

202− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"robots.txt`."} }

202+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d successfully to robots.txt"} }

203−

204− event: ping

205− data: {"type": "ping"}

206

203

207 event: content_block_stop

204 event: content_block_stop

208− data: {"type":"content_block_stop","index":0 }

205+ data: {"type":"content_block_stop","index":0 }

209−

210− event: ping

211− data: {"type": "ping"}

212−

213− event: ping

214− data: {"type": "ping"}

215

206

216 event: message_delta

207 event: message_delta

217− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":132,"cache_read_input_tokens":8664,"output_tokens":16} }

208+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":132,"cache_read_input_tokens":8572,"output_tokens":9} }

218

209

219 event: message_stop

210 event: message_stop

220− data: {"type":"message_stop" }

211+ data: {"type":"message_stop" }

221

212

222 headers:

213 headers:

223 Content-Type:

214 Content-Type:

224 - text/event-stream; charset=utf-8

215 - text/event-stream; charset=utf-8

225 status: 200 OK

216 status: 200 OK

226 code: 200

217 code: 200

227− duration: 2.018951292s

218+ duration: 2.052110416s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yaml+51−60

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,62 +25,59 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01FxSVzNELCauTsk6fSTg87j","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":154,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01RUyzrmHuHEw9TvX3rixMe3","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":154,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Web"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Web"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Scraping Content"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Content"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Search"}}

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Specific"} }

48 event: content_block_delta

45 event: content_block_delta

49− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Wor"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for"} }

51 event: content_block_delta

48 event: content_block_delta

52− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d"}}

49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Herman"} }

54 event: content_block_stop

51 event: content_block_stop

55− data: {"type":"content_block_stop","index":0 }

52+ data: {"type":"content_block_stop","index":0 }

57 event: message_delta

54 event: message_delta

58− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":154,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":154,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} }

60 event: message_stop

57 event: message_stop

61− data: {"type":"message_stop" }

58+ data: {"type":"message_stop"}

63 headers:

60 headers:

64 Content-Type:

61 Content-Type:

65 - text/event-stream; charset=utf-8

62 - text/event-stream; charset=utf-8

66 status: 200 OK

63 status: 200 OK

67 code: 200

64 code: 200

68− duration: 555.344458ms

65+ duration: 595.997458ms

69- id: 1

66- id: 1

70 request:

67 request:

71 proto: HTTP/1.1

68 proto: HTTP/1.1

72 proto_major: 1

69 proto_major: 1

73 proto_minor: 1

70 proto_minor: 1

74− content_length: 32107

71+ content_length: 31183

75 host: ""

72 host: ""

76− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

77 headers:

74 headers:

78 Accept:

75 Accept:

79 - application/json

76 - application/json

80 Content-Type:

77 Content-Type:

81 - application/json

78 - application/json

82 User-Agent:

79 User-Agent:

83− - Anthropic/Go 1.12.0

80+ - Anthropic/Go 1.14.0

84 url: https://api.anthropic.com/v1/messages

81 url: https://api.anthropic.com/v1/messages

85 method: POST

82 method: POST

86 response:

83 response:

@@ -90,65 +87,50 @@ interactions:

90 content_length: -1

87 content_length: -1

91 body: |+

88 body: |+

92 event: message_start

89 event: message_start

93− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01SiShydSKVnKzai3nv14vyP","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1814,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1814,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}

90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01RmP4xiG55hdipxUhwpavNL","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1723,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1723,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

95 event: content_block_start

92 event: content_block_start

96− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01GWL89Gxjkj9y4Eg5VDVbty","name":"fetch","input":{}} }

93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_019Zy35FKQEvqpif3dU6EsXR","name":"fetch","input":{}} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"url"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"https"} }

109

110 event: content_block_delta

95 event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"://ht"} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

112

113 event: content_block_delta

98 event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tpbi"} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"url\": \""} }

115

100

116 event: content_block_delta

101 event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n.or"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"https://ht"} }

118

103

119 event: content_block_delta

104 event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"g/h"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tpbin.org/ht"} }

121

106

122 event: content_block_delta

107 event: content_block_delta

123− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tml\""} }

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ml\""} }

124

109

125 event: content_block_delta

110 event: content_block_delta

126− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", "} }

111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"fo"} }

127

112

128 event: content_block_delta

113 event: content_block_delta

129− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"format\":"} }

114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rmat\":"} }

130

115

131 event: content_block_delta

116 event: content_block_delta

132− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"tex"} }

117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"text\"}"} }

133−

134− event: content_block_delta

135− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t\"}"} }

136

118

137 event: content_block_stop

119 event: content_block_stop

138− data: {"type":"content_block_stop","index":0 }

120+ data: {"type":"content_block_stop","index":0 }

139

121

140 event: message_delta

122 event: message_delta

141− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1814,"cache_read_input_tokens":6853,"output_tokens":75} }

123+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1723,"cache_read_input_tokens":6852,"output_tokens":75} }

142

124

143 event: message_stop

125 event: message_stop

144− data: {"type":"message_stop" }

126+ data: {"type":"message_stop" }

145

127

146 headers:

128 headers:

147 Content-Type:

129 Content-Type:

148 - text/event-stream; charset=utf-8

130 - text/event-stream; charset=utf-8

149 status: 200 OK

131 status: 200 OK

150 code: 200

132 code: 200

151− duration: 2.398155292s

133+ duration: 2.512604s

152- id: 2

134- id: 2

153 request:

135 request:

154 proto: HTTP/1.1

136 proto: HTTP/1.1

@@ -186,22 +168,22 @@ interactions:

186 - text/html; charset=utf-8

168 - text/html; charset=utf-8

187 status: 200 OK

169 status: 200 OK

188 code: 200

170 code: 200

189− duration: 461.971291ms

171+ duration: 1.437732167s

190- id: 3

172- id: 3

191 request:

173 request:

192 proto: HTTP/1.1

174 proto: HTTP/1.1

193 proto_major: 1

175 proto_major: 1

194 proto_minor: 1

176 proto_minor: 1

195− content_length: 36041

177+ content_length: 35117

196 host: ""

178 host: ""

197− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01GWL89Gxjkj9y4Eg5VDVbty\",\"input\":{\"format\":\"text\",\"url\":\"https://httpbin.org/html\"},\"name\":\"fetch\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01GWL89Gxjkj9y4Eg5VDVbty\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

179+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_019Zy35FKQEvqpif3dU6EsXR\",\"input\":{\"format\":\"text\",\"url\":\"https://httpbin.org/html\"},\"name\":\"fetch\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_019Zy35FKQEvqpif3dU6EsXR\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

198 headers:

180 headers:

199 Accept:

181 Accept:

200 - application/json

182 - application/json

201 Content-Type:

183 Content-Type:

202 - application/json

184 - application/json

203 User-Agent:

185 User-Agent:

204− - Anthropic/Go 1.12.0

186+ - Anthropic/Go 1.14.0

205 url: https://api.anthropic.com/v1/messages

187 url: https://api.anthropic.com/v1/messages

206 method: POST

188 method: POST

207 response:

189 response:

@@ -211,35 +193,44 @@ interactions:

211 content_length: -1

193 content_length: -1

212 body: |+

194 body: |+

213 event: message_start

195 event: message_start

214− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_013boRMcJ6WXTJLGeihTDTQn","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":980,"cache_read_input_tokens":8667,"cache_creation":{"ephemeral_5m_input_tokens":980,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

196+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01We6KJFYXWFHoBbvS3WUE3a","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":980,"cache_read_input_tokens":8575,"cache_creation":{"ephemeral_5m_input_tokens":980,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

215

197

216 event: content_block_start

198 event: content_block_start

217− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

199+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

218

200

219 event: content_block_delta

201 event: content_block_delta

220− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Yes"} }

202+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Yes"} }

221

203

222 event: content_block_delta

204 event: content_block_delta

223− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", it contains \"Herman\" (Herman"} }

205+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", it contains \"Herman Melville\""} }

224

206

225 event: ping

207 event: ping

226 data: {"type": "ping"}

208 data: {"type": "ping"}

227

209

228 event: content_block_delta

210 event: content_block_delta

229− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Melville) in the first line."} }

211+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" at the beginning."} }

212+

213+ event: ping

214+ data: {"type": "ping"}

230

215

231 event: content_block_stop

216 event: content_block_stop

232− data: {"type":"content_block_stop","index":0 }

217+ data: {"type":"content_block_stop","index":0 }

218+

219+ event: ping

220+ data: {"type": "ping"}

221+

222+ event: ping

223+ data: {"type": "ping"}

233

224

234 event: message_delta

225 event: message_delta

235− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":980,"cache_read_input_tokens":8667,"output_tokens":21} }

226+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":980,"cache_read_input_tokens":8575,"output_tokens":17} }

236

227

237 event: message_stop

228 event: message_stop

238− data: {"type":"message_stop" }

229+ data: {"type":"message_stop" }

239

230

240 headers:

231 headers:

241 Content-Type:

232 Content-Type:

242 - text/event-stream; charset=utf-8

233 - text/event-stream; charset=utf-8

243 status: 200 OK

234 status: 200 OK

244 code: 200

235 code: 200

245− duration: 2.482454875s

236+ duration: 3.182546s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yaml+50−35

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,59 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01FXonqh4CRaskWcSFpTBVeC","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01TRsP6tDfcqt14jh6xiLgC8","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Finding"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Fin"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Go"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files with"}}

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Glob"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" with"} }

47+

48+ event: content_block_delta

49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Glob"}}

48 event: content_block_stop

51 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

52+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

54 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} }

55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9}}

54 event: message_stop

57 event: message_stop

55− data: {"type":"message_stop" }

58+ data: {"type":"message_stop" }

57 headers:

60 headers:

58 Content-Type:

61 Content-Type:

59 - text/event-stream; charset=utf-8

62 - text/event-stream; charset=utf-8

60 status: 200 OK

63 status: 200 OK

61 code: 200

64 code: 200

62− duration: 550.481417ms

65+ duration: 582.017417ms

63- id: 1

66- id: 1

64 request:

67 request:

65 proto: HTTP/1.1

68 proto: HTTP/1.1

66 proto_major: 1

69 proto_major: 1

67 proto_minor: 1

70 proto_minor: 1

68− content_length: 32069

71+ content_length: 31145

69 host: ""

72 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

74 headers:

72 Accept:

75 Accept:

73 - application/json

76 - application/json

74 Content-Type:

77 Content-Type:

75 - application/json

78 - application/json

76 User-Agent:

79 User-Agent:

77− - Anthropic/Go 1.12.0

80+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

81 url: https://api.anthropic.com/v1/messages

79 method: POST

82 method: POST

80 response:

83 response:

@@ -84,53 +87,56 @@ interactions:

84 content_length: -1

87 content_length: -1

85 body: |+

88 body: |+

86 event: message_start

89 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_015aAoWx6ygTpFGHtvfoYkez","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1802,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1802,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01U6gxGnSnXXqzqQmZ8HBkbr","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1711,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1711,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}

89 event: content_block_start

92 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01CiThu8c8L9DgtKyE1RwQbU","name":"glob","input":{}} }

93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01QQQF8nkTSANmvN7T7QcgKy","name":"glob","input":{}} }

92 event: content_block_delta

95 event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}}

95 event: content_block_delta

98 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"patt"} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pat"} }

100

98 event: content_block_delta

101 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ern\": \"*"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tern\": \""} }

100

103

101 event: content_block_delta

104 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\"}"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"*.go"} }

106+

107+ event: content_block_delta

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

103

109

104 event: content_block_stop

110 event: content_block_stop

105− data: {"type":"content_block_stop","index":0 }

111+ data: {"type":"content_block_stop","index":0 }

106

112

107 event: message_delta

113 event: message_delta

108− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1802,"cache_read_input_tokens":6853,"output_tokens":52} }

114+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1711,"cache_read_input_tokens":6852,"output_tokens":52} }

109

115

110 event: message_stop

116 event: message_stop

111− data: {"type":"message_stop" }

117+ data: {"type":"message_stop" }

112

118

113 headers:

119 headers:

114 Content-Type:

120 Content-Type:

115 - text/event-stream; charset=utf-8

121 - text/event-stream; charset=utf-8

116 status: 200 OK

122 status: 200 OK

117 code: 200

123 code: 200

118− duration: 2.538935s

124+ duration: 2.731662667s

119- id: 2

125- id: 2

120 request:

126 request:

121 proto: HTTP/1.1

127 proto: HTTP/1.1

122 proto_major: 1

128 proto_major: 1

123 proto_minor: 1

129 proto_minor: 1

124− content_length: 32439

130+ content_length: 31515

125 host: ""

131 host: ""

126− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01CiThu8c8L9DgtKyE1RwQbU\",\"input\":{\"pattern\":\"*.go\"},\"name\":\"glob\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01CiThu8c8L9DgtKyE1RwQbU\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

132+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01QQQF8nkTSANmvN7T7QcgKy\",\"input\":{\"pattern\":\"*.go\"},\"name\":\"glob\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01QQQF8nkTSANmvN7T7QcgKy\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

127 headers:

133 headers:

128 Accept:

134 Accept:

129 - application/json

135 - application/json

130 Content-Type:

136 Content-Type:

131 - application/json

137 - application/json

132 User-Agent:

138 User-Agent:

133− - Anthropic/Go 1.12.0

139+ - Anthropic/Go 1.14.0

134 url: https://api.anthropic.com/v1/messages

140 url: https://api.anthropic.com/v1/messages

135 method: POST

141 method: POST

136 response:

142 response:

@@ -140,29 +146,38 @@ interactions:

140 content_length: -1

146 content_length: -1

141 body: |+

147 body: |+

142 event: message_start

148 event: message_start

143− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01VogCUV3zi9sLYPDKeEq64p","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":86,"cache_read_input_tokens":8655,"cache_creation":{"ephemeral_5m_input_tokens":86,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

149+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01ChnVVsE4Gffr3DmzfW151j","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":8563,"cache_creation":{"ephemeral_5m_input_tokens":86,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

144

150

145 event: content_block_start

151 event: content_block_start

146− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

152+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

147

153

148 event: content_block_delta

154 event: content_block_delta

149− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"`"} }

155+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main"} }

150

156

151 event: content_block_delta

157 event: content_block_delta

152− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main.go`"} }

158+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go"} }

159+

160+ event: ping

161+ data: {"type": "ping"}

153

162

154 event: content_block_stop

163 event: content_block_stop

155− data: {"type":"content_block_stop","index":0 }

164+ data: {"type":"content_block_stop","index":0 }

165+

166+ event: ping

167+ data: {"type": "ping"}

168+

169+ event: ping

170+ data: {"type": "ping"}

156

171

157 event: message_delta

172 event: message_delta

158− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":86,"cache_read_input_tokens":8655,"output_tokens":8} }

173+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":8563,"output_tokens":6} }

159

174

160 event: message_stop

175 event: message_stop

161− data: {"type":"message_stop" }

176+ data: {"type":"message_stop" }

162

177

163 headers:

178 headers:

164 Content-Type:

179 Content-Type:

165 - text/event-stream; charset=utf-8

180 - text/event-stream; charset=utf-8

166 status: 200 OK

181 status: 200 OK

167 code: 200

182 code: 200

168− duration: 2.1703915s

183+ duration: 3.063459333s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yaml+42−39

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,59 +25,56 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_012JHSdafaYGKa7doAmoqq17","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01RzWf6ES6f9YqJ9TCwx2PTM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Grep"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for "} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Package"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"'package' in Go"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Search"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" files with"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in Go Files"} }

47−

48− event: content_block_delta

49− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" grep"} }

51 event: content_block_stop

48 event: content_block_stop

52− data: {"type":"content_block_stop","index":0 }

49+ data: {"type":"content_block_stop","index":0 }

54 event: message_delta

51 event: message_delta

55− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":15} }

52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} }

57 event: message_stop

54 event: message_stop

58− data: {"type":"message_stop" }

55+ data: {"type":"message_stop" }

60 headers:

57 headers:

61 Content-Type:

58 Content-Type:

62 - text/event-stream; charset=utf-8

59 - text/event-stream; charset=utf-8

63 status: 200 OK

60 status: 200 OK

64 code: 200

61 code: 200

65− duration: 592.433333ms

62+ duration: 611.409917ms

66- id: 1

63- id: 1

67 request:

64 request:

68 proto: HTTP/1.1

65 proto: HTTP/1.1

69 proto_major: 1

66 proto_major: 1

70 proto_minor: 1

67 proto_minor: 1

71− content_length: 32067

68+ content_length: 31143

72 host: ""

69 host: ""

73− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

74 headers:

71 headers:

75 Accept:

72 Accept:

76 - application/json

73 - application/json

77 Content-Type:

74 Content-Type:

78 - application/json

75 - application/json

79 User-Agent:

76 User-Agent:

80− - Anthropic/Go 1.12.0

77+ - Anthropic/Go 1.14.0

81 url: https://api.anthropic.com/v1/messages

78 url: https://api.anthropic.com/v1/messages

82 method: POST

79 method: POST

83 response:

80 response:

@@ -87,34 +84,40 @@ interactions:

87 content_length: -1

84 content_length: -1

88 body: |+

85 body: |+

89 event: message_start

86 event: message_start

90− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01T85q5no8RwmV56PJA7PFXc","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1804,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1804,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_015hUDsFsNnCf1wPzRMZQTi6","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1713,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1713,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

92 event: content_block_start

89 event: content_block_start

93− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01BpVu9fuTSX8GtfcFtF4B5i","name":"grep","input":{}} }

90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01DTQVwdtsHh3cMufiwVNKpL","name":"grep","input":{}} }

91+

92+ event: content_block_delta

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

94+

95+ event: content_block_delta

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"patt"}}

95 event: content_block_delta

98 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ern\""}}

100

98 event: content_block_delta

101 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"patter"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"packa"} }

100

103

101 event: content_block_delta

104 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\": \"packag"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ge\""} }

103

106

104 event: content_block_delta

107 event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e\""} }

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"i"} }

106

109

107 event: content_block_delta

110 event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"include\":"} }

111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nclude\": \""} }

109

112

110 event: content_block_delta

113 event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"*.go\"}"} }

114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"*.go\"}"} }

112

115

113 event: content_block_stop

116 event: content_block_stop

114− data: {"type":"content_block_stop","index":0 }

117+ data: {"type":"content_block_stop","index":0 }

115

118

116 event: message_delta

119 event: message_delta

117− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1804,"cache_read_input_tokens":6853,"output_tokens":69} }

120+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1713,"cache_read_input_tokens":6852,"output_tokens":69} }

118

121

119 event: message_stop

122 event: message_stop

120 data: {"type":"message_stop" }

123 data: {"type":"message_stop" }

@@ -124,22 +127,22 @@ interactions:

124 - text/event-stream; charset=utf-8

127 - text/event-stream; charset=utf-8

125 status: 200 OK

128 status: 200 OK

126 code: 200

129 code: 200

127− duration: 2.190177334s

130+ duration: 2.153163666s

128- id: 2

131- id: 2

129 request:

132 request:

130 proto: HTTP/1.1

133 proto: HTTP/1.1

131 proto_major: 1

134 proto_major: 1

132 proto_minor: 1

135 proto_minor: 1

133− content_length: 32501

136+ content_length: 31585

134 host: ""

137 host: ""

135− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01BpVu9fuTSX8GtfcFtF4B5i\",\"input\":{\"include\":\"*.go\",\"pattern\":\"package\"},\"name\":\"grep\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01BpVu9fuTSX8GtfcFtF4B5i\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool/main.go:\\n Line 1: package main\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

138+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01DTQVwdtsHh3cMufiwVNKpL\",\"input\":{\"include\":\"*.go\",\"pattern\":\"package\"},\"name\":\"grep\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01DTQVwdtsHh3cMufiwVNKpL\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

136 headers:

139 headers:

137 Accept:

140 Accept:

138 - application/json

141 - application/json

139 Content-Type:

142 Content-Type:

140 - application/json

143 - application/json

141 User-Agent:

144 User-Agent:

142− - Anthropic/Go 1.12.0

145+ - Anthropic/Go 1.14.0

143 url: https://api.anthropic.com/v1/messages

146 url: https://api.anthropic.com/v1/messages

144 method: POST

147 method: POST

145 response:

148 response:

@@ -149,28 +152,28 @@ interactions:

149 content_length: -1

152 content_length: -1

150 body: |+

153 body: |+

151 event: message_start

154 event: message_start

152− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FAo1UdYq7G9CPG6q95Yrya","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8657,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

155+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01QXcSnyz6VZ9XZ6UW1wrdDd","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":8565,"cache_creation":{"ephemeral_5m_input_tokens":125,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

153

156

154 event: content_block_start

157 event: content_block_start

155− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

158+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

156

159

157 event: content_block_delta

160 event: content_block_delta

158− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

161+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

159

162

160 event: content_block_delta

163 event: content_block_delta

161− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 match in `main"} }

164+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 match in"} }

162

165

163 event: ping

166 event: ping

164 data: {"type": "ping"}

167 data: {"type": "ping"}

165

168

166 event: content_block_delta

169 event: content_block_delta

167− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go` at line 1."} }

170+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main.go at line 1"} }

168

171

169 event: content_block_stop

172 event: content_block_stop

170− data: {"type":"content_block_stop","index":0 }

173+ data: {"type":"content_block_stop","index":0 }

171

174

172 event: message_delta

175 event: message_delta

173− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8657,"output_tokens":19} }

176+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":8565,"output_tokens":16} }

174

177

175 event: message_stop

178 event: message_stop

176 data: {"type":"message_stop" }

179 data: {"type":"message_stop" }

@@ -180,4 +183,4 @@ interactions:

180 - text/event-stream; charset=utf-8

183 - text/event-stream; charset=utf-8

181 status: 200 OK

184 status: 200 OK

182 code: 200

185 code: 200

183− duration: 1.973956917s

186+ duration: 2.023175666s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yaml+33−45

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,53 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01WsuD73Q7FNCwhY6r9yesAF","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01EFPwwtF4fGytQfsssivQya","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"List"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"List"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in Current Directory"} }

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Current Directory"} }

48 event: content_block_stop

45 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

46+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

48 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} }

49+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8}}

54 event: message_stop

51 event: message_stop

55− data: {"type":"message_stop" }

52+ data: {"type":"message_stop" }

57 headers:

54 headers:

58 Content-Type:

55 Content-Type:

59 - text/event-stream; charset=utf-8

56 - text/event-stream; charset=utf-8

60 status: 200 OK

57 status: 200 OK

61 code: 200

58 code: 200

62− duration: 508.105833ms

59+ duration: 659.769125ms

63- id: 1

60- id: 1

64 request:

61 request:

65 proto: HTTP/1.1

62 proto: HTTP/1.1

66 proto_major: 1

63 proto_major: 1

67 proto_minor: 1

64 proto_minor: 1

68− content_length: 32061

65+ content_length: 31137

69 host: ""

66 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

67+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

68 headers:

72 Accept:

69 Accept:

73 - application/json

70 - application/json

74 Content-Type:

71 Content-Type:

75 - application/json

72 - application/json

76 User-Agent:

73 User-Agent:

77− - Anthropic/Go 1.12.0

74+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

75 url: https://api.anthropic.com/v1/messages

79 method: POST

76 method: POST

80 response:

77 response:

@@ -84,50 +81,50 @@ interactions:

84 content_length: -1

81 content_length: -1

85 body: |+

82 body: |+

86 event: message_start

83 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01EQmDNVC4ukLghSgfd5NSuj","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1800,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1800,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

84+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01948YnncZbU74ncr4verTH1","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1709,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1709,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}}

89 event: content_block_start

86 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_014cpfm3Fz4JYkeqR2cjbpNm","name":"ls","input":{}} }

87+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_013oz5axoenTuuisp8vWfEKE","name":"ls","input":{}} }

92 event: content_block_delta

89 event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

90+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

95 event: content_block_delta

92 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"path\":"}}

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"path\""} }

98 event: content_block_delta

95 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \".\"}"} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \".\"}"} }

100

101 event: content_block_stop

98 event: content_block_stop

102− data: {"type":"content_block_stop","index":0 }

99+ data: {"type":"content_block_stop","index":0 }

103

100

104 event: message_delta

101 event: message_delta

105− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1800,"cache_read_input_tokens":6853,"output_tokens":50} }

102+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1709,"cache_read_input_tokens":6852,"output_tokens":50} }

106

103

107 event: message_stop

104 event: message_stop

108− data: {"type":"message_stop" }

105+ data: {"type":"message_stop" }

109

106

110 headers:

107 headers:

111 Content-Type:

108 Content-Type:

112 - text/event-stream; charset=utf-8

109 - text/event-stream; charset=utf-8

113 status: 200 OK

110 status: 200 OK

114 code: 200

111 code: 200

115− duration: 2.599475s

112+ duration: 2.296407042s

116- id: 2

113- id: 2

117 request:

114 request:

118 proto: HTTP/1.1

115 proto: HTTP/1.1

119 proto_major: 1

116 proto_major: 1

120 proto_minor: 1

117 proto_minor: 1

121− content_length: 32445

118+ content_length: 31521

122 host: ""

119 host: ""

123− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_014cpfm3Fz4JYkeqR2cjbpNm\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_014cpfm3Fz4JYkeqR2cjbpNm\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

120+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_013oz5axoenTuuisp8vWfEKE\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_013oz5axoenTuuisp8vWfEKE\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

124 headers:

121 headers:

125 Accept:

122 Accept:

126 - application/json

123 - application/json

127 Content-Type:

124 Content-Type:

128 - application/json

125 - application/json

129 User-Agent:

126 User-Agent:

130− - Anthropic/Go 1.12.0

127+ - Anthropic/Go 1.14.0

131 url: https://api.anthropic.com/v1/messages

128 url: https://api.anthropic.com/v1/messages

132 method: POST

129 method: POST

133 response:

130 response:

@@ -137,38 +134,29 @@ interactions:

137 content_length: -1

134 content_length: -1

138 body: |+

135 body: |+

139 event: message_start

136 event: message_start

140− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01HYUPtHYzevgHi9AXRzhzaM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":97,"cache_read_input_tokens":8653,"cache_creation":{"ephemeral_5m_input_tokens":97,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

137+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01GwPREZa7mYgLyLKjpg1HqG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":97,"cache_read_input_tokens":8561,"cache_creation":{"ephemeral_5m_input_tokens":97,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

141

138

142 event: content_block_start

139 event: content_block_start

143− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

140+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

144

141

145 event: content_block_delta

142 event: content_block_delta

146− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"```"}}

143+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"go"} }

147

144

148 event: content_block_delta

145 event: content_block_delta

149− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\ngo.mod\nmain.go\n```"} }

146+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".mod, main.go"} }

150−

151− event: ping

152− data: {"type": "ping"}

153

147

154 event: content_block_stop

148 event: content_block_stop

155− data: {"type":"content_block_stop","index":0 }

149+ data: {"type":"content_block_stop","index":0 }

156−

157− event: ping

158− data: {"type": "ping"}

159−

160− event: ping

161− data: {"type": "ping"}

162

150

163 event: message_delta

151 event: message_delta

164− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":97,"cache_read_input_tokens":8653,"output_tokens":14} }

152+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":97,"cache_read_input_tokens":8561,"output_tokens":10} }

165

153

166 event: message_stop

154 event: message_stop

167− data: {"type":"message_stop" }

155+ data: {"type":"message_stop" }

168

156

169 headers:

157 headers:

170 Content-Type:

158 Content-Type:

171 - text/event-stream; charset=utf-8

159 - text/event-stream; charset=utf-8

172 status: 200 OK

160 status: 200 OK

173 code: 200

161 code: 200

174− duration: 2.239520333s

162+ duration: 2.462024416s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yaml+82−85

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,53 +25,56 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_012wZCQZFhzqRTZZ7xbNXT9P","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_011bN7xZaU6JvDk22sRZcraQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Modify"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Modify"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Greeting in"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Println"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main.go File"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Line"} }

44+

45+ event: content_block_delta

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in main.go"} }

45 event: content_block_stop

48 event: content_block_stop

46− data: {"type":"content_block_stop","index":0 }

49+ data: {"type":"content_block_stop","index":0 }

48 event: message_delta

51 event: message_delta

49− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

51 event: message_stop

54 event: message_stop

52− data: {"type":"message_stop" }

55+ data: {"type":"message_stop" }

54 headers:

57 headers:

55 Content-Type:

58 Content-Type:

56 - text/event-stream; charset=utf-8

59 - text/event-stream; charset=utf-8

57 status: 200 OK

60 status: 200 OK

58 code: 200

61 code: 200

59− duration: 593.423917ms

62+ duration: 1.071607083s

60- id: 1

63- id: 1

61 request:

64 request:

62 proto: HTTP/1.1

65 proto: HTTP/1.1

63 proto_major: 1

66 proto_major: 1

64 proto_minor: 1

67 proto_minor: 1

65− content_length: 32147

68+ content_length: 31223

66 host: ""

69 host: ""

67− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

68 headers:

71 headers:

69 Accept:

72 Accept:

70 - application/json

73 - application/json

71 Content-Type:

74 Content-Type:

72 - application/json

75 - application/json

73 User-Agent:

76 User-Agent:

74− - Anthropic/Go 1.12.0

77+ - Anthropic/Go 1.14.0

75 url: https://api.anthropic.com/v1/messages

78 url: https://api.anthropic.com/v1/messages

76 method: POST

79 method: POST

77 response:

80 response:

@@ -81,74 +84,74 @@ interactions:

81 content_length: -1

84 content_length: -1

82 body: |+

85 body: |+

83 event: message_start

86 event: message_start

84− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01TY1ypWiFAWPQkRLEmEo4Tt","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1832,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1832,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016Kg1UfhuFT1TjGbrtqtmaX","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1741,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1741,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

86 event: content_block_start

89 event: content_block_start

87− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

89 event: content_block_delta

92 event: content_block_delta

90− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll first"} }

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll rea"} }

92 event: content_block_delta

95 event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" check the content of main.go, then use mult"} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d the file first, then make both changes with mult"} }

95 event: ping

98 event: ping

96 data: {"type": "ping"}

99 data: {"type": "ping"}

100

98 event: content_block_delta

101 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"iedit to make both changes."} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"iedit."} }

100

103

101 event: content_block_stop

104 event: content_block_stop

102− data: {"type":"content_block_stop","index":0 }

105+ data: {"type":"content_block_stop","index":0 }

103

106

104 event: content_block_start

107 event: content_block_start

105− data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01EkVHzmaPGJju2LRYbGM3gJ","name":"view","input":{}} }

108+ data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01Dc4qPTcJkRkZoHoDVrd2rP","name":"view","input":{}} }

106

109

107 event: content_block_delta

110 event: content_block_delta

108− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }

111+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }

109

112

110 event: content_block_delta

113 event: content_block_delta

111− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"f"} }

114+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"file_"}}

112

115

113 event: content_block_delta

116 event: content_block_delta

114− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ile_path\""} }

117+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"path\": \"ma"} }

115

118

116 event: content_block_delta

119 event: content_block_delta

117− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":": \"main.g"} }

120+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"in.go"} }

118

121

119 event: content_block_delta

122 event: content_block_delta

120− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"o\"}"} }

123+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

121

124

122 event: content_block_stop

125 event: content_block_stop

123− data: {"type":"content_block_stop","index":1 }

126+ data: {"type":"content_block_stop","index":1 }

124

127

125 event: message_delta

128 event: message_delta

126− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1832,"cache_read_input_tokens":6853,"output_tokens":77} }

129+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1741,"cache_read_input_tokens":6852,"output_tokens":72} }

127

130

128 event: message_stop

131 event: message_stop

129− data: {"type":"message_stop"}

132+ data: {"type":"message_stop" }

130

133

131 headers:

134 headers:

132 Content-Type:

135 Content-Type:

133 - text/event-stream; charset=utf-8

136 - text/event-stream; charset=utf-8

134 status: 200 OK

137 status: 200 OK

135 code: 200

138 code: 200

136− duration: 2.025194292s

139+ duration: 2.508645583s

137- id: 2

140- id: 2

138 request:

141 request:

139 proto: HTTP/1.1

142 proto: HTTP/1.1

140 proto_major: 1

143 proto_major: 1

141 proto_minor: 1

144 proto_minor: 1

142− content_length: 32736

145+ content_length: 31795

143 host: ""

146 host: ""

144− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll first check the content of main.go, then use multiedit to make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

147+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first, then make both changes with multiedit.\",\"type\":\"text\"},{\"id\":\"toolu_01Dc4qPTcJkRkZoHoDVrd2rP\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Dc4qPTcJkRkZoHoDVrd2rP\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

145 headers:

148 headers:

146 Accept:

149 Accept:

147 - application/json

150 - application/json

148 Content-Type:

151 Content-Type:

149 - application/json

152 - application/json

150 User-Agent:

153 User-Agent:

151− - Anthropic/Go 1.12.0

154+ - Anthropic/Go 1.14.0

152 url: https://api.anthropic.com/v1/messages

155 url: https://api.anthropic.com/v1/messages

153 method: POST

156 method: POST

154 response:

157 response:

@@ -158,116 +161,122 @@ interactions:

158 content_length: -1

161 content_length: -1

159 body: |+

162 body: |+

160 event: message_start

163 event: message_start

161− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FWCXTK929EjksLY27954m7","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":141,"cache_read_input_tokens":8685,"cache_creation":{"ephemeral_5m_input_tokens":141,"ephemeral_1h_input_tokens":0},"output_tokens":25,"service_tier":"standard"}} }

164+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01349fDTHN7s5foGh5WPjjNb","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":136,"cache_read_input_tokens":8593,"cache_creation":{"ephemeral_5m_input_tokens":136,"ephemeral_1h_input_tokens":0},"output_tokens":29,"service_tier":"standard"}} }

162

165

163 event: content_block_start

166 event: content_block_start

164− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01SwJeR8LmvPpgUvmyVq4DRp","name":"multiedit","input":{}} }

167+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_016nP4VtJ5XVN4C14i4RN3Um","name":"multiedit","input":{}} }

168+

169+ event: content_block_delta

170+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

165

171

166 event: content_block_delta

172 event: content_block_delta

167− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

173+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pat"}}

168

174

169 event: content_block_delta

175 event: content_block_delta

170− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\""} }

176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"main.g"} }

171

177

172 event: content_block_delta

178 event: content_block_delta

173− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"file_pat"} }

179+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o\""} }

174

180

175 event: content_block_delta

181 event: content_block_delta

176− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"m"} }

182+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"edi"} }

177

183

178 event: content_block_delta

184 event: content_block_delta

179− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain.go\""} }

185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ts\": [{\"old"} }

180

186

181 event: content_block_delta

187 event: content_block_delta

182− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"edi"} }

188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_str"} }

183

189

184 event: content_block_delta

190 event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ts\": [{"}}

191+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing"} }

186

192

187 event: content_block_delta

193 event: content_block_delta

188− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"old_str"} }

194+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":\"fu"} }

189

195

190 event: content_block_delta

196 event: content_block_delta

191− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing"}}

197+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nc "} }

192

198

193 event: content_block_delta

199 event: content_block_delta

194− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":\"\\tfmt"} }

200+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main() {\\n\\t"} }

195

201

196 event: content_block_delta

202 event: content_block_delta

197− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".Println(\\\""} }

203+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fmt.Println("} }

198

204

199 event: content_block_delta

205 event: content_block_delta

200− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Hel"} }

206+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\"H"} }

201

207

202 event: content_block_delta

208 event: content_block_delta

203− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo, Worl"} }

209+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ello, Wor"} }

204

210

205 event: content_block_delta

211 event: content_block_delta

206− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d!\\\")\""} }

212+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ld!\\\")\",\"ne"}}

207

213

208 event: content_block_delta

214 event: content_block_delta

209− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":",\"new_s"} }

215+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"w_s"} }

210

216

211 event: content_block_delta

217 event: content_block_delta

212− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tring"} }

218+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tring\""} }

213

219

214 event: content_block_delta

220 event: content_block_delta

215− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":\"\\t// Gr"} }

221+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":":\"func ma"} }

216

222

217 event: content_block_delta

223 event: content_block_delta

218− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"eet"} }

224+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"in("} }

219

225

220 event: content_block_delta

226 event: content_block_delta

221− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing"} }

227+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":") {\\n\\t//"} }

222

228

223 event: content_block_delta

229 event: content_block_delta

224− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n\\tf"} }

230+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" G"} }

225

231

226 event: content_block_delta

232 event: content_block_delta

227− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mt.Printl"} }

233+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"reeting\\n\\"} }

228

234

229 event: content_block_delta

235 event: content_block_delta

230− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n(\\\"Hell"} }

236+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tfmt.Prin"} }

231

237

232 event: content_block_delta

238 event: content_block_delta

233− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o, Cru"} }

239+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tln(\\\"Hello"} }

234

240

235 event: content_block_delta

241 event: content_block_delta

236− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh!\\\")\"}"} }

242+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", Crush!\\\")"} }

237

243

238 event: content_block_delta

244 event: content_block_delta

239− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"]}"} }

245+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

246+

247+ event: content_block_delta

248+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"]}"} }

240

249

241 event: content_block_stop

250 event: content_block_stop

242− data: {"type":"content_block_stop","index":0 }

251+ data: {"type":"content_block_stop","index":0 }

243

252

244 event: message_delta

253 event: message_delta

245− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":141,"cache_read_input_tokens":8685,"output_tokens":133} }

254+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":136,"cache_read_input_tokens":8593,"output_tokens":147} }

246

255

247 event: message_stop

256 event: message_stop

248− data: {"type":"message_stop" }

257+ data: {"type":"message_stop" }

249

258

250 headers:

259 headers:

251 Content-Type:

260 Content-Type:

252 - text/event-stream; charset=utf-8

261 - text/event-stream; charset=utf-8

253 status: 200 OK

262 status: 200 OK

254 code: 200

263 code: 200

255− duration: 2.222343667s

264+ duration: 2.43646825s

256- id: 3

265- id: 3

257 request:

266 request:

258 proto: HTTP/1.1

267 proto: HTTP/1.1

259 proto_major: 1

268 proto_major: 1

260 proto_minor: 1

269 proto_minor: 1

261− content_length: 33275

270+ content_length: 32364

262 host: ""

271 host: ""

263− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll first check the content of main.go, then use multiedit to make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01EkVHzmaPGJju2LRYbGM3gJ\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01SwJeR8LmvPpgUvmyVq4DRp\",\"input\":{\"edits\":[{\"new_string\":\"\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\",\"old_string\":\"\\tfmt.Println(\\\"Hello, World!\\\")\"}],\"file_path\":\"main.go\"},\"name\":\"multiedit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SwJeR8LmvPpgUvmyVq4DRp\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

272+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first, then make both changes with multiedit.\",\"type\":\"text\"},{\"id\":\"toolu_01Dc4qPTcJkRkZoHoDVrd2rP\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Dc4qPTcJkRkZoHoDVrd2rP\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_016nP4VtJ5XVN4C14i4RN3Um\",\"input\":{\"edits\":[{\"new_string\":\"func main() {\\n\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\"}],\"file_path\":\"main.go\"},\"name\":\"multiedit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_016nP4VtJ5XVN4C14i4RN3Um\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

264 headers:

273 headers:

265 Accept:

274 Accept:

266 - application/json

275 - application/json

267 Content-Type:

276 Content-Type:

268 - application/json

277 - application/json

269 User-Agent:

278 User-Agent:

270− - Anthropic/Go 1.12.0

279+ - Anthropic/Go 1.14.0

271 url: https://api.anthropic.com/v1/messages

280 url: https://api.anthropic.com/v1/messages

272 method: POST

281 method: POST

273 response:

282 response:

@@ -277,38 +286,26 @@ interactions:

277 content_length: -1

286 content_length: -1

278 body: |+

287 body: |+

279 event: message_start

288 event: message_start

280− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_018XV2bezokrWMT4B8rr8dnp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":178,"cache_read_input_tokens":8826,"cache_creation":{"ephemeral_5m_input_tokens":178,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

289+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_018BziK5si5QR6kdh7aajjXM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":192,"cache_read_input_tokens":8729,"cache_creation":{"ephemeral_5m_input_tokens":192,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

281

290

282 event: content_block_start

291 event: content_block_start

283− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

292+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

284−

285− event: content_block_delta

286− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

287

293

288 event: content_block_delta

294 event: content_block_delta

289− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":". Changed \"Hello, World!\" to \"Hello"} }

295+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

290−

291− event: ping

292− data: {"type": "ping"}

293−

294− event: content_block_delta

295− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", Crush!\" and added the comment above the println"} }

296−

297− event: content_block_delta

298− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"."} }

299

296

300 event: content_block_stop

297 event: content_block_stop

301− data: {"type":"content_block_stop","index":0 }

298+ data: {"type":"content_block_stop","index":0 }

302

299

303 event: message_delta

300 event: message_delta

304− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":178,"cache_read_input_tokens":8826,"output_tokens":26}}

301+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":192,"cache_read_input_tokens":8729,"output_tokens":4} }

305

302

306 event: message_stop

303 event: message_stop

307− data: {"type":"message_stop" }

304+ data: {"type":"message_stop" }

308

305

309 headers:

306 headers:

310 Content-Type:

307 Content-Type:

311 - text/event-stream; charset=utf-8

308 - text/event-stream; charset=utf-8

312 status: 200 OK

309 status: 200 OK

313 code: 200

310 code: 200

314− duration: 2.106580459s

311+ duration: 2.259016875s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yaml+42−51

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,59 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01QG9K82nFdNjFtQk7NoK5QB","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_017eiqBiGHLGyQu82xGfSB8X","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Parallel"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Parallel"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go File"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go File"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Search and Directory"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Search"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Listing"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" and Directory"} }

47+

48+ event: content_block_delta

49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Listing"} }

48 event: content_block_stop

51 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

52+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

54 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":12} }

54 event: message_stop

57 event: message_stop

55− data: {"type":"message_stop" }

58+ data: {"type":"message_stop" }

57 headers:

60 headers:

58 Content-Type:

61 Content-Type:

59 - text/event-stream; charset=utf-8

62 - text/event-stream; charset=utf-8

60 status: 200 OK

63 status: 200 OK

61 code: 200

64 code: 200

62− duration: 514.665167ms

65+ duration: 756.29075ms

63- id: 1

66- id: 1

64 request:

67 request:

65 proto: HTTP/1.1

68 proto: HTTP/1.1

66 proto_major: 1

69 proto_major: 1

67 proto_minor: 1

70 proto_minor: 1

68− content_length: 32158

71+ content_length: 31234

69 host: ""

72 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

74 headers:

72 Accept:

75 Accept:

73 - application/json

76 - application/json

74 Content-Type:

77 Content-Type:

75 - application/json

78 - application/json

76 User-Agent:

79 User-Agent:

77− - Anthropic/Go 1.12.0

80+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

81 url: https://api.anthropic.com/v1/messages

79 method: POST

82 method: POST

80 response:

83 response:

@@ -84,77 +87,68 @@ interactions:

84 content_length: -1

87 content_length: -1

85 body: |+

88 body: |+

86 event: message_start

89 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_0145i9s7oaHwEazjgovKd81D","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1821,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01E5WTyY6paaSBLH5CCLpWmL","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1730,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1730,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

89 event: content_block_start

92 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01TeEXyjpFCqWrAh2Wd8qBh7","name":"glob","input":{}} }

93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_012q67vksWc4BpunyFosfU6P","name":"glob","input":{}} }

92 event: content_block_delta

95 event: content_block_delta

93 data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

96 data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

95 event: content_block_delta

98 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pat"} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pattern\""} }

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tern"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\":"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"**/*"} }

106

100

107 event: content_block_delta

101 event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".g"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"**/*.g"}}

109

103

110 event: content_block_delta

104 event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o\"}"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o\"}"} }

112

106

113 event: content_block_stop

107 event: content_block_stop

114− data: {"type":"content_block_stop","index":0 }

108+ data: {"type":"content_block_stop","index":0 }

115

109

116 event: content_block_start

110 event: content_block_start

117− data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01N8sSFCLzvYCd2uXbz4jUGT","name":"ls","input":{}} }

111+ data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_013WXRBgESthmyknEGQGdX2v","name":"ls","input":{}} }

118

112

119 event: content_block_delta

113 event: content_block_delta

120− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }

114+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} }

121

115

122 event: content_block_delta

116 event: content_block_delta

123− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"path\": \""} }

117+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"path\": \"."} }

124

118

125 event: content_block_delta

119 event: content_block_delta

126− data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":".\"}"} }

120+ data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

127

121

128 event: content_block_stop

122 event: content_block_stop

129− data: {"type":"content_block_stop","index":1 }

123+ data: {"type":"content_block_stop","index":1 }

130

124

131 event: message_delta

125 event: message_delta

132− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"output_tokens":86} }

126+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1730,"cache_read_input_tokens":6852,"output_tokens":86} }

133

127

134 event: message_stop

128 event: message_stop

135− data: {"type":"message_stop" }

129+ data: {"type":"message_stop" }

136

130

137 headers:

131 headers:

138 Content-Type:

132 Content-Type:

139 - text/event-stream; charset=utf-8

133 - text/event-stream; charset=utf-8

140 status: 200 OK

134 status: 200 OK

141 code: 200

135 code: 200

142− duration: 2.443706708s

136+ duration: 2.8894285s

143- id: 2

137- id: 2

144 request:

138 request:

145 proto: HTTP/1.1

139 proto: HTTP/1.1

146 proto_major: 1

140 proto_major: 1

147 proto_minor: 1

141 proto_minor: 1

148− content_length: 32839

142+ content_length: 31915

149 host: ""

143 host: ""

150− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01TeEXyjpFCqWrAh2Wd8qBh7\",\"input\":{\"pattern\":\"**/*.go\"},\"name\":\"glob\",\"type\":\"tool_use\"},{\"id\":\"toolu_01N8sSFCLzvYCd2uXbz4jUGT\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01TeEXyjpFCqWrAh2Wd8qBh7\",\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"},{\"tool_use_id\":\"toolu_01N8sSFCLzvYCd2uXbz4jUGT\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

144+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_012q67vksWc4BpunyFosfU6P\",\"input\":{\"pattern\":\"**/*.go\"},\"name\":\"glob\",\"type\":\"tool_use\"},{\"id\":\"toolu_013WXRBgESthmyknEGQGdX2v\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_012q67vksWc4BpunyFosfU6P\",\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"},{\"tool_use_id\":\"toolu_013WXRBgESthmyknEGQGdX2v\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

151 headers:

145 headers:

152 Accept:

146 Accept:

153 - application/json

147 - application/json

154 Content-Type:

148 Content-Type:

155 - application/json

149 - application/json

156 User-Agent:

150 User-Agent:

157− - Anthropic/Go 1.12.0

151+ - Anthropic/Go 1.14.0

158 url: https://api.anthropic.com/v1/messages

152 url: https://api.anthropic.com/v1/messages

159 method: POST

153 method: POST

160 response:

154 response:

@@ -164,38 +158,35 @@ interactions:

164 content_length: -1

158 content_length: -1

165 body: |+

159 body: |+

166 event: message_start

160 event: message_start

167− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01CfHH9AC59iAZSPJ4Ec3Khu","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":7,"cache_creation_input_tokens":207,"cache_read_input_tokens":8674,"cache_creation":{"ephemeral_5m_input_tokens":207,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

161+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_015pSPzxf44b5dNKqog1dGK3","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":8582,"cache_creation":{"ephemeral_5m_input_tokens":207,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

168

162

169 event: content_block_start

163 event: content_block_start

170− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

164+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

171

165

172 event: content_block_delta

166 event: content_block_delta

173− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

167+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

174

168

175 event: content_block_delta

169 event: content_block_delta

176− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 Go file:"} }

170+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 Go file: `main.go`"} }

177

171

178 event: ping

172 event: ping

179 data: {"type": "ping"}

173 data: {"type": "ping"}

180

174

181 event: content_block_delta

175 event: content_block_delta

182− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" `main.go`\n\nCurrent directory contains"} }

176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\n\nDirectory contains: `go.mod`, `main.go`"} }

183−

184− event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":": `go.mod` and `main.go`"} }

186

177

187 event: content_block_stop

178 event: content_block_stop

188 data: {"type":"content_block_stop","index":0 }

179 data: {"type":"content_block_stop","index":0 }

189

180

190 event: message_delta

181 event: message_delta

191− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":7,"cache_creation_input_tokens":207,"cache_read_input_tokens":8674,"output_tokens":31} }

182+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":8582,"output_tokens":29} }

192

183

193 event: message_stop

184 event: message_stop

194− data: {"type":"message_stop" }

185+ data: {"type":"message_stop" }

195

186

196 headers:

187 headers:

197 Content-Type:

188 Content-Type:

198 - text/event-stream; charset=utf-8

189 - text/event-stream; charset=utf-8

199 status: 200 OK

190 status: 200 OK

200 code: 200

191 code: 200

201− duration: 2.043650083s

192+ duration: 2.458768125s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yaml+38−35

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,56 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01AosjrFVVXCqAidJohxn6E7","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_0126vEnUQ7o7aRzupozLAUnp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Rea"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Review"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Go"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Module"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Module"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Details"}}

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Dependencies"} }

48 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

49+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":7}}

52+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":7} }

54 event: message_stop

55− data: {"type":"message_stop" }

55+ data: {"type":"message_stop" }

57 headers:

58 Content-Type:

59 - text/event-stream; charset=utf-8

60 status: 200 OK

61 code: 200

62− duration: 550.275666ms

62+ duration: 600.96675ms

63- id: 1

64 request:

65 proto: HTTP/1.1

66 proto_major: 1

67 proto_minor: 1

68− content_length: 32031

68+ content_length: 31107

69 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

70+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

72 Accept:

73 - application/json

74 Content-Type:

75 - application/json

76 User-Agent:

77− - Anthropic/Go 1.12.0

77+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

79 method: POST

80 response:

@@ -84,53 +84,56 @@ interactions:

84 content_length: -1

85 body: |+

86 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01EfY8UeWMNayyJJUGdNLeWM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1796,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1796,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

87+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01CD6STj9jSvU2NiHtRTjqPh","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1705,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1705,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

89 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_016p6McX7tVqThB1FwChHmMm","name":"view","input":{}} }

90+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01UXMHkffqyrw6nGSyUp36Ap","name":"view","input":{}} }

92 event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}}

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

95 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path\""} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file"} }

98 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"go.mod"} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_path\": \"go"} }

100

101 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".mod"} }

103+

104+ event: content_block_delta

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} }

103

106

104 event: content_block_stop

107 event: content_block_stop

105− data: {"type":"content_block_stop","index":0 }

108+ data: {"type":"content_block_stop","index":0 }

106

109

107 event: message_delta

110 event: message_delta

108− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1796,"cache_read_input_tokens":6853,"output_tokens":55} }

111+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1705,"cache_read_input_tokens":6852,"output_tokens":55} }

109

112

110 event: message_stop

113 event: message_stop

111− data: {"type":"message_stop" }

114+ data: {"type":"message_stop" }

112

115

113 headers:

116 headers:

114 Content-Type:

117 Content-Type:

115 - text/event-stream; charset=utf-8

118 - text/event-stream; charset=utf-8

116 status: 200 OK

119 status: 200 OK

117 code: 200

120 code: 200

118− duration: 2.078621417s

121+ duration: 2.50069s

119- id: 2

122- id: 2

120 request:

123 request:

121 proto: HTTP/1.1

124 proto: HTTP/1.1

122 proto_major: 1

125 proto_major: 1

123 proto_minor: 1

126 proto_minor: 1

124− content_length: 32441

127+ content_length: 31517

125 host: ""

128 host: ""

126− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_016p6McX7tVqThB1FwChHmMm\",\"input\":{\"file_path\":\"go.mod\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_016p6McX7tVqThB1FwChHmMm\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

129+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01UXMHkffqyrw6nGSyUp36Ap\",\"input\":{\"file_path\":\"go.mod\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01UXMHkffqyrw6nGSyUp36Ap\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

127 headers:

130 headers:

128 Accept:

131 Accept:

129 - application/json

132 - application/json

130 Content-Type:

133 Content-Type:

131 - application/json

134 - application/json

132 User-Agent:

135 User-Agent:

133− - Anthropic/Go 1.12.0

136+ - Anthropic/Go 1.14.0

134 url: https://api.anthropic.com/v1/messages

137 url: https://api.anthropic.com/v1/messages

135 method: POST

138 method: POST

136 response:

139 response:

@@ -140,28 +143,28 @@ interactions:

140 content_length: -1

143 content_length: -1

141 body: |+

144 body: |+

142 event: message_start

145 event: message_start

143− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_019XZCDz8LmAGBwQsusVMYtg","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":96,"cache_read_input_tokens":8649,"cache_creation":{"ephemeral_5m_input_tokens":96,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

146+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01JvxrCQL1MKHWHg1ouZ6tQF","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":96,"cache_read_input_tokens":8557,"cache_creation":{"ephemeral_5m_input_tokens":96,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

144

147

145 event: content_block_start

148 event: content_block_start

146− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

149+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

147

150

148 event: content_block_delta

151 event: content_block_delta

149− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"```"} }

152+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Go"} }

150

153

151 event: content_block_delta

154 event: content_block_delta

152− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\nmodule example.com/testproject\n\ngo 1.23"} }

155+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" 1.23, module example.com/testproject, no"}}

153

156

154 event: ping

157 event: ping

155 data: {"type": "ping"}

158 data: {"type": "ping"}

156

159

157 event: content_block_delta

160 event: content_block_delta

158− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"\n```"} }

161+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" dependencies."} }

159

162

160 event: ping

163 event: ping

161 data: {"type": "ping"}

164 data: {"type": "ping"}

162

165

163 event: content_block_stop

166 event: content_block_stop

164− data: {"type":"content_block_stop","index":0 }

167+ data: {"type":"content_block_stop","index":0 }

165

168

166 event: ping

169 event: ping

167 data: {"type": "ping"}

170 data: {"type": "ping"}

@@ -170,7 +173,7 @@ interactions:

170 data: {"type": "ping"}

173 data: {"type": "ping"}

171

174

172 event: message_delta

175 event: message_delta

173− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":96,"cache_read_input_tokens":8649,"output_tokens":20} }

176+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":96,"cache_read_input_tokens":8557,"output_tokens":20} }

174

177

175 event: message_stop

178 event: message_stop

176 data: {"type":"message_stop" }

179 data: {"type":"message_stop" }

@@ -180,4 +183,4 @@ interactions:

180 - text/event-stream; charset=utf-8

183 - text/event-stream; charset=utf-8

181 status: 200 OK

184 status: 200 OK

182 code: 200

185 code: 200

183− duration: 2.382524875s

186+ duration: 2.386795834s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yaml+19−19

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,28 +25,28 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01FAWvBoccVMmLTBJwcdyBep","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_014kwk8LeCrDLVUHwtvdWe5y","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31 data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Quick"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Quick"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Chat"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Chat"}}

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Start"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Start"} }

45 event: content_block_stop

46− data: {"type":"content_block_stop","index":0 }

46+ data: {"type":"content_block_stop","index":0 }

48 event: message_delta

49− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":6} }

49+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":6} }

51 event: message_stop

52 data: {"type":"message_stop" }

@@ -56,22 +56,22 @@ interactions:

56 - text/event-stream; charset=utf-8

57 status: 200 OK

58 code: 200

59− duration: 733.150917ms

59+ duration: 748.485709ms

60- id: 1

61 request:

62 proto: HTTP/1.1

63 proto_major: 1

64 proto_minor: 1

65− content_length: 32021

65+ content_length: 31097

66 host: ""

67− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Hello\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/simple_test\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

67+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Hello\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

68 headers:

69 Accept:

70 - application/json

71 Content-Type:

72 - application/json

73 User-Agent:

74− - Anthropic/Go 1.12.0

74+ - Anthropic/Go 1.14.0

75 url: https://api.anthropic.com/v1/messages

76 method: POST

77 response:

@@ -81,29 +81,29 @@ interactions:

81 content_length: -1

82 body: |+

83 event: message_start

84− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016wHt1RPkbhRGGRDo89QjdQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":8644,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":8644,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

84+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FyJYBee7XM5UZMHDRiVpz7","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":8552,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":8552,"ephemeral_1h_input_tokens":0},"output_tokens":5,"service_tier":"standard"}} }

86 event: content_block_start

87− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

87+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

89 event: content_block_delta

90− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello! How"} }

90+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello! I'm ready"} }

92 event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" can I help you today?"} }

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" to help. What would you like to do?"} }

95 event: content_block_stop

96− data: {"type":"content_block_stop","index":0 }

96+ data: {"type":"content_block_stop","index":0 }

98 event: message_delta

99− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":8644,"cache_read_input_tokens":0,"output_tokens":12}}

99+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":8552,"cache_read_input_tokens":0,"output_tokens":18} }

100

101 event: message_stop

102− data: {"type":"message_stop" }

102+ data: {"type":"message_stop" }

103

104 headers:

105 Content-Type:

106 - text/event-stream; charset=utf-8

107 status: 200 OK

108 code: 200

109− duration: 2.528825917s

109+ duration: 2.3804415s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yaml+55−43

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,59 +25,59 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_0137phYsnpb3ZLZ6xWV4o1qc","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_013YipYtB4pPD2dsY23bK1nj","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} }

30 event: content_block_start

31 data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching "} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"'func main' in"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Repos"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go repos"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for Main"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" with"} }

48 event: content_block_delta

49− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Functions"} }

49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Sourcegraph"}}

51 event: content_block_stop

52− data: {"type":"content_block_stop","index":0}

52+ data: {"type":"content_block_stop","index":0 }

54 event: message_delta

55− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} }

55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":18} }

57 event: message_stop

58− data: {"type":"message_stop" }

58+ data: {"type":"message_stop" }

60 headers:

61 Content-Type:

62 - text/event-stream; charset=utf-8

63 status: 200 OK

64 code: 200

65− duration: 561.671875ms

65+ duration: 954.205583ms

66- id: 1

67 request:

68 proto: HTTP/1.1

69 proto_major: 1

70 proto_minor: 1

71− content_length: 32081

71+ content_length: 31157

72 host: ""

73− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

74 headers:

75 Accept:

76 - application/json

77 Content-Type:

78 - application/json

79 User-Agent:

80− - Anthropic/Go 1.12.0

80+ - Anthropic/Go 1.14.0

81 url: https://api.anthropic.com/v1/messages

82 method: POST

83 response:

@@ -87,50 +87,53 @@ interactions:

87 content_length: -1

88 body: |+

89 event: message_start

90− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01L5zZBpdDM2uiQ2eLwF7YxE","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1807,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01NoLeZ1AJ2R7Fnk4fMtY9A6","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1716,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

92 event: content_block_start

93− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01SSVxWDkehx1WmUUkrDb3xg","name":"sourcegraph","input":{}} }

93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01WxTwSoBycRW1bxYFLJUCnA","name":"sourcegraph","input":{}} }

94+

95+ event: content_block_delta

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}}

95 event: content_block_delta

98 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"quer"} }

100

98 event: content_block_delta

101 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\""} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"y\": \"lan"}}

100

103

101 event: content_block_delta

104 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"query"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"g:go fun"} }

103

106

104 event: content_block_delta

107 event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"lang:go "} }

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c ma"} }

106

109

107 event: content_block_delta

110 event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"func "} }

111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"in\""} }

109

112

110 event: content_block_delta

113 event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main\""} }

114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"cou"} }

112

115

113 event: content_block_delta

116 event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \""} }

117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nt\":"} }

115

118

116 event: content_block_delta

119 event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"count\": 10}"} }

120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" 20}"} }

118

121

119 event: content_block_stop

122 event: content_block_stop

120− data: {"type":"content_block_stop","index":0 }

123+ data: {"type":"content_block_stop","index":0 }

121

124

122 event: message_delta

125 event: message_delta

123− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"output_tokens":74} }

126+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"output_tokens":74} }

124

127

125 event: message_stop

128 event: message_stop

126− data: {"type":"message_stop" }

129+ data: {"type":"message_stop" }

127

130

128 headers:

131 headers:

129 Content-Type:

132 Content-Type:

130 - text/event-stream; charset=utf-8

133 - text/event-stream; charset=utf-8

131 status: 200 OK

134 status: 200 OK

132 code: 200

135 code: 200

133− duration: 2.650093625s

136+ duration: 2.412315s

134- id: 2

137- id: 2

135 request:

138 request:

136 proto: HTTP/1.1

139 proto: HTTP/1.1

@@ -152,28 +155,28 @@ interactions:

152 proto_minor: 0

155 proto_minor: 0

153 content_length: -1

156 content_length: -1

154 uncompressed: true

157 uncompressed: true

155− body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/pingguoxueyuan/gostudy"},"file":{"path":"listen15/defer/main.go","url":"/github.com/pingguoxueyuan/gostudy/-/blob/listen15/defer/main.go","content":"package main\n\nimport (\n\t\"fmt\"\n)\n\nfunc funcA() int {\n\tx := 5\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn x\n}\n\nfunc funcB() (x int) {\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn 5\n}\n\nfunc funcC() (y int) {\n\tx := 5\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn x\n}\n\nfunc funcD() (x int) {\n\tdefer func(x int) {\n\t\tx += 1\n\t}(x)\n\treturn 5\n}\n\nfunc main() {\n\t//fmt.Println(funcA())\n\t//fmt.Println(funcB())\n\t//fmt.Println(funcC())\n\tfmt.Println(funcD())\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":36,"offsetAndLengths":[[0,9]]},{"preview":"\t//fmt.Println(funcA())","lineNumber":37,"offsetAndLengths":[[15,4]]},{"preview":"\t//fmt.Println(funcB())","lineNumber":38,"offsetAndLengths":[[15,4]]},{"preview":"\t//fmt.Println(funcC())","lineNumber":39,"offsetAndLengths":[[15,4]]},{"preview":"\tfmt.Println(funcD())","lineNumber":40,"offsetAndLengths":[[13,4]]},{"preview":"func funcA() int {","lineNumber":6,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":8,"offsetAndLengths":[[7,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func funcB() (x int) {","lineNumber":14,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":15,"offsetAndLengths":[[7,4]]},{"preview":"func funcC() (y int) {","lineNumber":21,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":23,"offsetAndLengths":[[7,4]]},{"preview":"func funcD() (x int) {","lineNumber":29,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func(x int) {","lineNumber":30,"offsetAndLengths":[[7,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/Zhouchaowen/golang-tutorial"},"file":{"path":"12-library/8-error/ch_1/main.go","url":"/github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go","content":"package main\n\nimport (\n\t\"errors\"\n\t\"fmt\"\n)\n\nfunc func1() error {\n\treturn errors.New(\"func1 error\")\n}\n\nfunc func2() error {\n\treturn fmt.Errorf(\"func2 error: %w\", func1())\n}\n\nfunc main() {\n\terr := func2()\n\tif err != nil {\n\t\tfmt.Println(err)\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":15,"offsetAndLengths":[[0,9]]},{"preview":"\terr := func2()","lineNumber":16,"offsetAndLengths":[[8,4]]},{"preview":"func func1() error {","lineNumber":7,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\treturn errors.New(\"func1 error\")","lineNumber":8,"offsetAndLengths":[[20,4]]},{"preview":"func func2() error {","lineNumber":11,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\treturn fmt.Errorf(\"func2 error: %w\", func1())","lineNumber":12,"offsetAndLengths":[[20,4],[38,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/lynda"},"file":{"path":"cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go","url":"/github.com/GoesToEleven/lynda/-/blob/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc greeting() {\n\tfmt.Println(\"Hello world!\")\n}\n\nfunc main() {\n\tgreeting()\n}\n\n/*\nAll material is licensed under the Apache License Version 2.0, January 2004\nhttp://www.apache.org/licenses/LICENSE-2.0\n*/\n"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]}]}}}}'

158+ body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":33,"offsetAndLengths":[[0,9]]},{"preview":"\tFuncA()","lineNumber":34,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncB()","lineNumber":35,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncC()","lineNumber":36,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncD()","lineNumber":37,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncE()","lineNumber":38,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncF()","lineNumber":39,"offsetAndLengths":[[1,4]]},{"preview":"func FuncE() {","lineNumber":4,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncE\")","lineNumber":5,"offsetAndLengths":[[14,4]]},{"preview":"func FuncD() {","lineNumber":8,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncE()","lineNumber":9,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncD\")","lineNumber":10,"offsetAndLengths":[[14,4]]},{"preview":"func FuncC() {","lineNumber":13,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncD()","lineNumber":14,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncC\")","lineNumber":15,"offsetAndLengths":[[14,4]]},{"preview":"func FuncB() {","lineNumber":18,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncC()","lineNumber":19,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncB\")","lineNumber":20,"offsetAndLengths":[[14,4]]},{"preview":"func FuncA() {","lineNumber":23,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncB()","lineNumber":24,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncA\")","lineNumber":25,"offsetAndLengths":[[14,4]]},{"preview":"func FuncF() {","lineNumber":28,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncF\")","lineNumber":29,"offsetAndLengths":[[14,4]]},{"preview":"\tFuncE()","lineNumber":30,"offsetAndLengths":[[1,4]]}]}]}}}}'

156 headers:

159 headers:

157 Content-Type:

160 Content-Type:

158 - application/json

161 - application/json

159 status: 200 OK

162 status: 200 OK

160 code: 200

163 code: 200

161− duration: 1.454512083s

164+ duration: 1.459370042s

162- id: 3

165- id: 3

163 request:

166 request:

164 proto: HTTP/1.1

167 proto: HTTP/1.1

165 proto_major: 1

168 proto_major: 1

166 proto_minor: 1

169 proto_minor: 1

167− content_length: 40202

170+ content_length: 39032

168 host: ""

171 host: ""

169− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01SSVxWDkehx1WmUUkrDb3xg\",\"input\":{\"count\":10,\"query\":\"lang:go func main\"},\"name\":\"sourcegraph\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SSVxWDkehx1WmUUkrDb3xg\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/pingguoxueyuan/gostudy/listen15/defer/main.go\\n\\nURL: /github.com/pingguoxueyuan/gostudy/-/blob/listen15/defer/main.go\\n\\n```\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| func main() {\\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| \\t//fmt.Println(funcA())\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcB())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcC())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\tfmt.Println(funcD())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| func funcA() int {\\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tdefer func() {\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n```\\n\\n```\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| func funcB() (x int) {\\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n```\\n\\n```\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| \\tdefer func() {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n```\\n\\n```\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| func funcC() (y int) {\\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n```\\n\\n```\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tdefer func() {\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n```\\n\\n```\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| func funcD() (x int) {\\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n```\\n\\n```\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| \\tdefer func(x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n```\\n\\n## Result 2: github.com/Zhouchaowen/golang-tutorial/12-library/8-error/ch_1/main.go\\n\\nURL: /github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go\\n\\n```\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| func main() {\\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| \\terr := func2()\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| func func1() error {\\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| \\treturn errors.New(\\\"func1 error\\\")\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| func func2() error {\\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n```\\n\\n```\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n```\\n\\n## Result 3: github.com/GoesToEleven/lynda/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/lynda/-/blob/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| func main() {\\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n13| /*\\n14| All material is licensed under the Apache License Version 2.0, January 2004\\n15| http://www.apache.org/licenses/LICENSE-2.0\\n16| */\\n17| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n```\\n\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

172+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01WxTwSoBycRW1bxYFLJUCnA\",\"input\":{\"count\":20,\"query\":\"lang:go func main\"},\"name\":\"sourcegraph\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01WxTwSoBycRW1bxYFLJUCnA\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n```\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| \\tFuncB()\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n```\\n\\n```\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tfmt.Println(\\\"FuncA\\\")\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n```\\n\\n```\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| func FuncF() {\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n```\\n\\n```\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| \\tfmt.Println(\\\"FuncF\\\")\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n```\\n\\n```\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tFuncE()\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n```\\n\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

170 headers:

173 headers:

171 Accept:

174 Accept:

172 - application/json

175 - application/json

173 Content-Type:

176 Content-Type:

174 - application/json

177 - application/json

175 User-Agent:

178 User-Agent:

176− - Anthropic/Go 1.12.0

179+ - Anthropic/Go 1.14.0

177 url: https://api.anthropic.com/v1/messages

180 url: https://api.anthropic.com/v1/messages

178 method: POST

181 method: POST

179 response:

182 response:

@@ -183,34 +186,43 @@ interactions:

183 content_length: -1

186 content_length: -1

184 body: |+

187 body: |+

185 event: message_start

188 event: message_start

186− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LRLuMdSjNZajNN2EUxAd4C","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":3612,"cache_read_input_tokens":8660,"cache_creation":{"ephemeral_5m_input_tokens":3612,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

189+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Eoh2qucbrabMAdn8updnvB","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":3890,"cache_read_input_tokens":8568,"cache_creation":{"ephemeral_5m_input_tokens":3890,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

187

190

188 event: content_block_start

191 event: content_block_start

189− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

192+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

190

193

191 event: content_block_delta

194 event: content_block_delta

192− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

195+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} }

193

196

194 event: content_block_delta

197 event: content_block_delta

195− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 30 matches across 30 files. The"} }

198+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 30 matches across public Go repositories. All results"} }

196

199

197 event: ping

200 event: ping

198 data: {"type": "ping"}

201 data: {"type": "ping"}

199

202

200 event: content_block_delta

203 event: content_block_delta

201− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" search returned Go repositories containing `func main` declarations"} }

204+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" are from `github.com/jcalab"} }

205+

206+ event: content_block_delta

207+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"ro/uscope/assets/"} }

208+

209+ event: content_block_delta

210+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"gobacktrace/main.go"} }

211+

212+ event: content_block_delta

213+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"` showing a `func main()` that"} }

202

214

203 event: content_block_delta

215 event: content_block_delta

204− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", including examples from tutorial repositories showing"} }

216+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" calls multiple functions (FuncA through"} }

205

217

206 event: content_block_delta

218 event: content_block_delta

207− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" various Go language features like defer statements, error handling, and function expressions."} }

219+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" FuncF)."} }

208

220

209 event: content_block_stop

221 event: content_block_stop

210− data: {"type":"content_block_stop","index":0 }

222+ data: {"type":"content_block_stop","index":0 }

211

223

212 event: message_delta

224 event: message_delta

213− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":3612,"cache_read_input_tokens":8660,"output_tokens":47} }

225+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":3890,"cache_read_input_tokens":8568,"output_tokens":63} }

214

226

215 event: message_stop

227 event: message_stop

216 data: {"type":"message_stop" }

228 data: {"type":"message_stop" }

@@ -220,4 +232,4 @@ interactions:

220 - text/event-stream; charset=utf-8

232 - text/event-stream; charset=utf-8

221 status: 200 OK

233 status: 200 OK

222 code: 200

234 code: 200

223− duration: 2.523495s

235+ duration: 2.518737541s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yaml+75−78

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,53 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_0124XpcSuB61ZBx1SPUnu1Qb","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01V2gbirhEyjs4DiYnh93EC9","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Update"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Update"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main.go hello"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go Hello"}}

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" print"} }

44−

45− event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Print"} }

48 event: content_block_stop

45 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

46+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

48 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} }

49+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} }

54 event: message_stop

51 event: message_stop

55− data: {"type":"message_stop" }

52+ data: {"type":"message_stop" }

57 headers:

54 headers:

58 Content-Type:

55 Content-Type:

59 - text/event-stream; charset=utf-8

56 - text/event-stream; charset=utf-8

60 status: 200 OK

57 status: 200 OK

61 code: 200

58 code: 200

62− duration: 648.821083ms

59+ duration: 700.907542ms

63- id: 1

60- id: 1

64 request:

61 request:

65 proto: HTTP/1.1

62 proto: HTTP/1.1

66 proto_major: 1

63 proto_major: 1

67 proto_minor: 1

64 proto_minor: 1

68− content_length: 32087

65+ content_length: 31163

69 host: ""

66 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

67+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

68 headers:

72 Accept:

69 Accept:

73 - application/json

70 - application/json

74 Content-Type:

71 Content-Type:

75 - application/json

72 - application/json

76 User-Agent:

73 User-Agent:

77− - Anthropic/Go 1.12.0

74+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

75 url: https://api.anthropic.com/v1/messages

79 method: POST

76 method: POST

80 response:

77 response:

@@ -84,62 +81,56 @@ interactions:

84 content_length: -1

81 content_length: -1

85 body: |+

82 body: |+

86 event: message_start

83 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01WDos6sXG37avomBTwjHnLi","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1807,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

84+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01BGZLUc1twLVbQk15aHwo1v","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1716,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

89 event: content_block_start

86 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_012eFK8SiD9DLuu1r9G1riKx","name":"view","input":{}} }

87+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_011XTovZHHrqbeMteDcXFDxD","name":"view","input":{}} }

91−

92− event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

95 event: content_block_delta

89 event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\""} }

90+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

98 event: content_block_delta

92 event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fi"} }

93+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pat"} }

100

101 event: content_block_delta

95 event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"le_p"} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": "} }

103

104 event: content_block_delta

98 event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ath"} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"main.go"} }

106

100

107 event: content_block_delta

101 event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"main"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"}}

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\"}"} }

112

103

113 event: content_block_stop

104 event: content_block_stop

114− data: {"type":"content_block_stop","index":0 }

105+ data: {"type":"content_block_stop","index":0 }

115

106

116 event: message_delta

107 event: message_delta

117− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1807,"cache_read_input_tokens":6853,"output_tokens":55} }

108+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"output_tokens":55} }

118

109

119 event: message_stop

110 event: message_stop

120− data: {"type":"message_stop" }

111+ data: {"type":"message_stop" }

121

112

122 headers:

113 headers:

123 Content-Type:

114 Content-Type:

124 - text/event-stream; charset=utf-8

115 - text/event-stream; charset=utf-8

125 status: 200 OK

116 status: 200 OK

126 code: 200

117 code: 200

127− duration: 2.504401167s

118+ duration: 2.543036458s

128- id: 2

119- id: 2

129 request:

120 request:

130 proto: HTTP/1.1

121 proto: HTTP/1.1

131 proto_major: 1

122 proto_major: 1

132 proto_minor: 1

123 proto_minor: 1

133− content_length: 32569

124+ content_length: 31645

134 host: ""

125 host: ""

135− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

126+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

136 headers:

127 headers:

137 Accept:

128 Accept:

138 - application/json

129 - application/json

139 Content-Type:

130 Content-Type:

140 - application/json

131 - application/json

141 User-Agent:

132 User-Agent:

142− - Anthropic/Go 1.12.0

133+ - Anthropic/Go 1.14.0

143 url: https://api.anthropic.com/v1/messages

134 url: https://api.anthropic.com/v1/messages

144 method: POST

135 method: POST

145 response:

136 response:

@@ -149,113 +140,122 @@ interactions:

149 content_length: -1

140 content_length: -1

150 body: |+

141 body: |+

151 event: message_start

142 event: message_start

152− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_011Y6PAeHJdg3Ph6ZFLMNuwG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8660,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":25,"service_tier":"standard"}} }

143+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01SxNBCVbJi3vF81CoCZVean","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":8568,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":33,"service_tier":"standard"}} }

153

144

154 event: content_block_start

145 event: content_block_start

155− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_019M2MmqUbzyvMfw9WaD3VFa","name":"edit","input":{}} }

146+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_017DGAG8X47hb2gawfBGnBz1","name":"edit","input":{}}}

156

147

157 event: content_block_delta

148 event: content_block_delta

158 data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

149 data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

159

150

160 event: content_block_delta

151 event: content_block_delta

161− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_p"} }

152+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path\""} }

153+

154+ event: content_block_delta

155+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"m"} }

156+

157+ event: content_block_delta

158+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain"} }

159+

160+ event: content_block_delta

161+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\""} }

162

163 event: content_block_delta

164− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ath\": \"mai"} }

164+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"ol"} }

165

166 event: content_block_delta

167− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n."} }

167+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d_st"} }

168

169 event: content_block_delta

170− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"go\""} }

170+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ring\": \"func"} }

171

172 event: content_block_delta

173− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"old_"} }

173+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" main()"} }

174

175 event: content_block_delta

176− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stri"} }

176+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" {\\n\\tfmt"} }

177

178 event: content_block_delta

179− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ng\": \"fu"} }

179+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".P"} }

180

181 event: content_block_delta

182− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nc main() {\\"} }

182+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ri"} }

183

184 event: content_block_delta

185− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\\tfmt."} }

185+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntln(\\\"Hell"} }

186

187 event: content_block_delta

188− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Println(\\\""} }

188+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o, Worl"} }

189

190 event: content_block_delta

191− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Hello, "} }

191+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d!"} }

192

193 event: content_block_delta

194− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Wo"} }

194+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\")\\n}\""} }

195

196 event: content_block_delta

197− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rld!\\\")"} }

197+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"new_str"} }

198

199 event: content_block_delta

200− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n}\""} }

200+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing\": \"f"} }

201

202 event: content_block_delta

203− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"new_stri"} }

203+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"unc main()"} }

204

205 event: content_block_delta

206− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ng\": \"func "}}

206+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" {\\n\\tf"} }

207

208 event: content_block_delta

209− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main() {\\n\\"} }

209+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mt."} }

210

211 event: content_block_delta

212− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tfmt.Pri"} }

212+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Println"} }

213

214 event: content_block_delta

215− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntln(\\\"hello"} }

215+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"(\\\"hel"} }

216

217 event: content_block_delta

218− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" from cr"} }

218+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo f"} }

219

220 event: content_block_delta

221− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush\\\""} }

221+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rom crush"} }

222

223 event: content_block_delta

224− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":")\\"}}

224+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\")\\n"} }

225

226 event: content_block_delta

227− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n}\"}"} }

227+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"}\"}"} }

228

229 event: content_block_stop

230− data: {"type":"content_block_stop","index":0 }

230+ data: {"type":"content_block_stop","index":0 }

231

232 event: message_delta

233− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":120,"cache_read_input_tokens":8660,"output_tokens":123}}

233+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":8568,"output_tokens":123} }

234

235 event: message_stop

236− data: {"type":"message_stop" }

236+ data: {"type":"message_stop" }

237

238 headers:

239 Content-Type:

240 - text/event-stream; charset=utf-8

241 status: 200 OK

242 code: 200

243− duration: 2.590338541s

243+ duration: 2.447528917s

244- id: 3

245 request:

246 proto: HTTP/1.1

247 proto_major: 1

248 proto_minor: 1

249− content_length: 33115

249+ content_length: 32191

250 host: ""

251− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_012eFK8SiD9DLuu1r9G1riKx\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_019M2MmqUbzyvMfw9WaD3VFa\",\"input\":{\"file_path\":\"main.go\",\"new_string\":\"func main() {\\n\\tfmt.Println(\\\"hello from crush\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"},\"name\":\"edit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_019M2MmqUbzyvMfw9WaD3VFa\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

251+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_017DGAG8X47hb2gawfBGnBz1\",\"input\":{\"file_path\":\"main.go\",\"new_string\":\"func main() {\\n\\tfmt.Println(\\\"hello from crush\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"},\"name\":\"edit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_017DGAG8X47hb2gawfBGnBz1\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

252 headers:

253 Accept:

254 - application/json

255 Content-Type:

256 - application/json

257 User-Agent:

258− - Anthropic/Go 1.12.0

258+ - Anthropic/Go 1.14.0

259 url: https://api.anthropic.com/v1/messages

260 method: POST

261 response:

@@ -265,29 +265,26 @@ interactions:

265 content_length: -1

266 body: |+

267 event: message_start

268− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016L6sSaeRFwHpTNycXatjPG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":175,"cache_read_input_tokens":8780,"cache_creation":{"ephemeral_5m_input_tokens":175,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

268+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_0156vJYCmnoDHddugupfiaQP","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":175,"cache_read_input_tokens":8688,"cache_creation":{"ephemeral_5m_input_tokens":175,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

269

270 event: content_block_start

271− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

271+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

272−

273− event: content_block_delta

274− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

275

272

276 event: content_block_delta

273 event: content_block_delta

277− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"."} }

274+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

278

275

279 event: content_block_stop

276 event: content_block_stop

280− data: {"type":"content_block_stop","index":0 }

277+ data: {"type":"content_block_stop","index":0 }

281

278

282 event: message_delta

279 event: message_delta

283− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":175,"cache_read_input_tokens":8780,"output_tokens":5} }

280+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":175,"cache_read_input_tokens":8688,"output_tokens":4} }

284

281

285 event: message_stop

282 event: message_stop

286− data: {"type":"message_stop" }

283+ data: {"type":"message_stop" }

287

284

288 headers:

285 headers:

289 Content-Type:

286 Content-Type:

290 - text/event-stream; charset=utf-8

287 - text/event-stream; charset=utf-8

291 status: 200 OK

288 status: 200 OK

292 code: 200

289 code: 200

293− duration: 3.520432916s

290+ duration: 2.651659958s

internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yaml+45−93

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - Anthropic/Go 1.12.0

18+ - Anthropic/Go 1.14.0

19 url: https://api.anthropic.com/v1/messages

20 method: POST

21 response:

@@ -25,56 +25,59 @@ interactions:

25 content_length: -1

26 body: |+

27 event: message_start

28− data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01JMWchmGYjGvwhk1QHW8zM2","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

28+ data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01Vo9QhQKAZCU1jVuEKC4btz","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

30 event: content_block_start

31− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

31+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

33 event: content_block_delta

34− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} }

34+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} }

36 event: content_block_delta

37− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" JSON"} }

37+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" config"} }

39 event: ping

40 data: {"type": "ping"}

42 event: content_block_delta

43− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Configuration"} }

43+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".json with"} }

45 event: content_block_delta

46− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" File"} }

46+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" initial"} }

47+

48+ event: content_block_delta

49+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" settings"} }

48 event: content_block_stop

51 event: content_block_stop

49− data: {"type":"content_block_stop","index":0 }

52+ data: {"type":"content_block_stop","index":0 }

51 event: message_delta

54 event: message_delta

52− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":7} }

55+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} }

54 event: message_stop

57 event: message_stop

55− data: {"type":"message_stop" }

58+ data: {"type":"message_stop" }

57 headers:

60 headers:

58 Content-Type:

61 Content-Type:

59 - text/event-stream; charset=utf-8

62 - text/event-stream; charset=utf-8

60 status: 200 OK

63 status: 200 OK

61 code: 200

64 code: 200

62− duration: 525.572291ms

65+ duration: 631.479458ms

63- id: 1

66- id: 1

64 request:

67 request:

65 proto: HTTP/1.1

68 proto: HTTP/1.1

66 proto_major: 1

69 proto_major: 1

67 proto_minor: 1

70 proto_minor: 1

68− content_length: 32124

71+ content_length: 31200

69 host: ""

72 host: ""

70− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

73+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

71 headers:

74 headers:

72 Accept:

75 Accept:

73 - application/json

76 - application/json

74 Content-Type:

77 Content-Type:

75 - application/json

78 - application/json

76 User-Agent:

79 User-Agent:

77− - Anthropic/Go 1.12.0

80+ - Anthropic/Go 1.14.0

78 url: https://api.anthropic.com/v1/messages

81 url: https://api.anthropic.com/v1/messages

79 method: POST

82 method: POST

80 response:

83 response:

@@ -84,113 +87,80 @@ interactions:

84 content_length: -1

87 content_length: -1

85 body: |+

88 body: |+

86 event: message_start

89 event: message_start

87− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01GtViPWmhueXgG64JgCJ7m2","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"cache_creation":{"ephemeral_5m_input_tokens":1821,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

90+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01XtasmW2DxtD4cnkmhd1C33","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1730,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1730,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

89 event: content_block_start

92 event: content_block_start

90− data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_014LZ2qfDhfKZ43DAp3QDDGd","name":"write","input":{}} }

93+ data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_0111efm6idsGJJAJHVk5PN6N","name":"write","input":{}} }

91−

92− event: content_block_delta

93− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

94−

95− event: content_block_delta

96− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path"}}

97−

98− event: content_block_delta

99− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"/tmp/cr"} }

100−

101− event: content_block_delta

102− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush-t"} }

103−

104− event: content_block_delta

105− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"est/Te"} }

106−

107− event: content_block_delta

108− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stCoderAgen"} }

109−

110− event: content_block_delta

111− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/anthrop"} }

112−

113− event: content_block_delta

114− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ic-"} }

115−

116− event: content_block_delta

117− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"son"} }

118

119 event: content_block_delta

95 event: content_block_delta

120− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"net/write"} }

96+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} }

121

122 event: content_block_delta

98 event: content_block_delta

123− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_to"} }

99+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path"} }

124

100

125 event: content_block_delta

101 event: content_block_delta

126− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ol/co"} }

102+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"config"} }

127

103

128 event: content_block_delta

104 event: content_block_delta

129− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nfig.j"} }

105+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".json\""} }

130

106

131 event: content_block_delta

107 event: content_block_delta

132− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"so"} }

108+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"content\""}}

133

109

134 event: content_block_delta

110 event: content_block_delta

135− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\""} }

111+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"{\\"} }

136

112

137 event: content_block_delta

113 event: content_block_delta

138− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"co"} }

114+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"name"} }

139

115

140 event: content_block_delta

116 event: content_block_delta

141− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntent\": \""} }

117+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\":"} }

142

118

143 event: content_block_delta

119 event: content_block_delta

144− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\\\"name\\\":"} }

120+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \\\"test\\\","} }

145

121

146 event: content_block_delta

122 event: content_block_delta

147− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \\\"test\\\", \\"} }

123+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \\\"version\\"} }

148

124

149 event: content_block_delta

125 event: content_block_delta

150− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"vers"} }

126+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": "}}

151

127

152 event: content_block_delta

128 event: content_block_delta

153− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ion\\\""} }

129+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\"1"}}

154

130

155 event: content_block_delta

131 event: content_block_delta

156− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \\"} }

132+ data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".0.0\\\"}\"}"} }

157−

158− event: content_block_delta

159− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"1.0.0\\\""} }

160−

161− event: content_block_delta

162− data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"}\"}"} }

163

133

164 event: content_block_stop

134 event: content_block_stop

165− data: {"type":"content_block_stop","index":0 }

135+ data: {"type":"content_block_stop","index":0 }

166

136

167 event: message_delta

137 event: message_delta

168− data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":1821,"cache_read_input_tokens":6853,"output_tokens":109}}

138+ data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1730,"cache_read_input_tokens":6852,"output_tokens":87} }

169

139

170 event: message_stop

140 event: message_stop

171− data: {"type":"message_stop" }

141+ data: {"type":"message_stop" }

172

142

173 headers:

143 headers:

174 Content-Type:

144 Content-Type:

175 - text/event-stream; charset=utf-8

145 - text/event-stream; charset=utf-8

176 status: 200 OK

146 status: 200 OK

177 code: 200

147 code: 200

178− duration: 3.78905875s

148+ duration: 2.252533792s

179- id: 2

149- id: 2

180 request:

150 request:

181 proto: HTTP/1.1

151 proto: HTTP/1.1

182 proto_major: 1

152 proto_major: 1

183 proto_minor: 1

153 proto_minor: 1

184− content_length: 32693

154+ content_length: 31710

185 host: ""

155 host: ""

186− body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_014LZ2qfDhfKZ43DAp3QDDGd\",\"input\":{\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\"},\"name\":\"write\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_014LZ2qfDhfKZ43DAp3QDDGd\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nFile successfully written: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\\n\\u003c/result\\u003e\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n\\u003cmemory_instructions\\u003e\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccommunication_style\\u003e\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n\\u003cexample\\u003e\\nuser: 2 + 2\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what is 2+2?\\nassistant: 4\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: is 11 a prime number?\\nassistant: true\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n\\u003c/example\\u003e\\n\\n\\u003cexample\\u003e\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n\\u003c/example\\u003e\\n\\n\\u003c/communication_style\\u003e\\n\\n\\u003cproactiveness\\u003e\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfollowing_conversations\\u003e\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n\\u003c/following_conversations\\u003e\\n\\n\\u003ccode_style\\u003e\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n\\u003c/code_style\\u003e\\n\\n\\u003cdoing_tasks\\u003e\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n\\u003c/doing_tasks\\u003e\\n\\n\\u003ctool_use\\u003e\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n\\u003c/tool_use\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

156+ body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_0111efm6idsGJJAJHVk5PN6N\",\"input\":{\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\",\"file_path\":\"config.json\"},\"name\":\"write\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_0111efm6idsGJJAJHVk5PN6N\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nFile successfully written: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\\n\\u003c/result\\u003e\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"

187 headers:

157 headers:

188 Accept:

158 Accept:

189 - application/json

159 - application/json

190 Content-Type:

160 Content-Type:

191 - application/json

161 - application/json

192 User-Agent:

162 User-Agent:

193− - Anthropic/Go 1.12.0

163+ - Anthropic/Go 1.14.0

194 url: https://api.anthropic.com/v1/messages

164 url: https://api.anthropic.com/v1/messages

195 method: POST

165 method: POST

196 response:

166 response:

@@ -200,37 +170,19 @@ interactions:

200 content_length: -1

170 content_length: -1

201 body: |+

171 body: |+

202 event: message_start

172 event: message_start

203− data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_012m9RadV58H14GKHAK3vy9V","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":155,"cache_read_input_tokens":8674,"cache_creation":{"ephemeral_5m_input_tokens":155,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

173+ data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Vh3sXDUeWbkvbyKPgMqnL5","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":133,"cache_read_input_tokens":8582,"cache_creation":{"ephemeral_5m_input_tokens":133,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} }

204

174

205 event: content_block_start

175 event: content_block_start

206− data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

176+ data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }

207−

208− event: content_block_delta

209− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} }

210−

211− event: content_block_delta

212− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d `config.json` with the specifie"}}

213−

214− event: ping

215− data: {"type": "ping"}

216

177

217 event: content_block_delta

178 event: content_block_delta

218− data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d content."}}

179+ data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} }

219−

220− event: ping

221− data: {"type": "ping"}

222

180

223 event: content_block_stop

181 event: content_block_stop

224− data: {"type":"content_block_stop","index":0}

182+ data: {"type":"content_block_stop","index":0 }

225−

226− event: ping

227− data: {"type": "ping"}

228−

229− event: ping

230− data: {"type": "ping"}

231

183

232 event: message_delta

184 event: message_delta

233− data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":155,"cache_read_input_tokens":8674,"output_tokens":14} }

185+ data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":133,"cache_read_input_tokens":8582,"output_tokens":4} }

234

186

235 event: message_stop

187 event: message_stop

236 data: {"type":"message_stop" }

188 data: {"type":"message_stop" }

@@ -240,4 +192,4 @@ interactions:

240 - text/event-stream; charset=utf-8

192 - text/event-stream; charset=utf-8

241 status: 200 OK

193 status: 200 OK

242 code: 200

194 code: 200

243− duration: 2.228601375s

195+ duration: 2.434365708s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/bash_tool.yaml+186−49

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,21 +24,23 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ZpHu07mjyHpmu9"}

27+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"5WTtJ1eUbukmUe"}

29− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"h9r9mxks3R"}

29+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"AcHAYVWbkS"}

31− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"NTcfKnqOQlN"}

31+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"aOZz7fwokXQlkz"}

33− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"qAkWebioRfq"}

33+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"SkN5keGHx06"}

35− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Bash"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"qXC3rYFLeO0"}

35+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"PCTyR9QwLQU"}

37− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Command"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"nTQFNfGG"}

37+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Bash"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"igMrV8UPPfL"}

39− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Rwwmcw2d0q"}

39+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Command"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"6zycsBVC"}

41+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"3b8Ax2Ojnq"}

42+

41− data: {"id":"chatcmpl-CQ4QjZPsahyhwu5jZlu72OhkUmAUd","object":"chat.completion.chunk","created":1760329593,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":5,"total_tokens":144,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ZXCURxqgWFFyvP"}

43+ data: {"id":"chatcmpl-CToETSSbaB9YSlMZKEcIMOx60Csyx","object":"chat.completion.chunk","created":1761220641,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":6,"total_tokens":145,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ilSb8f05W03KWu"}

43 data: [DONE]

45 data: [DONE]

@@ -47,22 +49,22 @@ interactions:

47 - text/event-stream; charset=utf-8

49 - text/event-stream; charset=utf-8

48 status: 200 OK

50 status: 200 OK

49 code: 200

51 code: 200

50− duration: 564.410458ms

52+ duration: 921.929791ms

51- id: 1

53- id: 1

52 request:

54 request:

53 proto: HTTP/1.1

55 proto: HTTP/1.1

54 proto_major: 1

56 proto_major: 1

55 proto_minor: 1

57 proto_minor: 1

56− content_length: 30720

58+ content_length: 29876

57 host: ""

59 host: ""

58− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

60+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

59 headers:

61 headers:

60 Accept:

62 Accept:

61 - application/json

63 - application/json

62 Content-Type:

64 Content-Type:

63 - application/json

65 - application/json

64 User-Agent:

66 User-Agent:

65− - OpenAI/Go 2.3.0

67+ - OpenAI/Go 2.7.1

66 url: https://api.openai.com/v1/chat/completions

68 url: https://api.openai.com/v1/chat/completions

67 method: POST

69 method: POST

68 response:

70 response:

@@ -71,59 +73,111 @@ interactions:

71 proto_minor: 0

73 proto_minor: 0

72 content_length: -1

74 content_length: -1

73 body: |+

75 body: |+

74− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Dtaw7aR0fdx9F1BjgDKVoQZs","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"WmX9YER8GVMw"}

76+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null},"finish_reason":null}],"obfuscation":"nWqzf1s"}

77+

78+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_zxRiwoXvL3JbHjuK2wfHPuFs","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null}],"obfuscation":"utjX0A3kS6HFFaS"}

79+

80+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"VHuowH8TNjWM9"}

81+

82+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"th\": "}}]},"finish_reason":null}],"obfuscation":"Nt4LlxGt0mFq"}

83+

84+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/tmp/"}}]},"finish_reason":null}],"obfuscation":"fl5Tpt60fZ4"}

85+

86+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"crus"}}]},"finish_reason":null}],"obfuscation":"79ErhgoObYAzxw"}

87+

88+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"h-tes"}}]},"finish_reason":null}],"obfuscation":"TJLpGAbMyYlCj"}

89+

90+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t/Test"}}]},"finish_reason":null}],"obfuscation":"osNuMBXcNfVK"}

91+

92+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Code"}}]},"finish_reason":null}],"obfuscation":"EXk5Rn2DafIU97"}

93+

94+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"rAgen"}}]},"finish_reason":null}],"obfuscation":"3P41kXZ6rNpL0"}

95+

96+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t/open"}}]},"finish_reason":null}],"obfuscation":"4oCL8CAsxuix"}

97+

98+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai-g"}}]},"finish_reason":null}],"obfuscation":"3QERq3nbt6AKDg"}

99+

100+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt-5/"}}]},"finish_reason":null}],"obfuscation":"cwka1DGiMbaPN"}

101+

102+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"bash_t"}}]},"finish_reason":null}],"obfuscation":"SEC0Q66JbKqt"}

103+

104+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ool\""}}]},"finish_reason":null}],"obfuscation":"Dc8VnnSN2PSfU"}

105+

106+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":", \"de"}}]},"finish_reason":null}],"obfuscation":"NjKkSvYPVLBv"}

107+

108+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pth\": "}}]},"finish_reason":null}],"obfuscation":"nqyvpeQPFm2"}

109+

110+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1}"}}]},"finish_reason":null}],"obfuscation":""}

111+

112+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"id":"call_aKrRv7qkfWJU7W8RpfGscsLN","type":"function","function":{"name":"bash","arguments":""}}]},"finish_reason":null}],"obfuscation":"spbOL8uhgpgsF"}

113+

114+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{\"co"}}]},"finish_reason":null}],"obfuscation":"l1TaqVAaLhbJQ"}

115

76− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"CC69a3K7zTa5N0u"}

116+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"mmand"}}]},"finish_reason":null}],"obfuscation":"twm5gJTdVf2vy"}

117

78− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y5xefR9hBCm"}

118+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"\": \"pr"}}]},"finish_reason":null}],"obfuscation":"ISs6EQkAPK"}

119

80− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ub8tFLg3aijuX"}

120+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"intf"}}]},"finish_reason":null}],"obfuscation":"GQczPsRKFaliXl"}

121

82− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"printf"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rvGOAvSiXSAN"}

122+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":" 'hel"}}]},"finish_reason":null}],"obfuscation":"n6vz7X5YWr7tR"}

123

84− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '%"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r5zUKWn1JePE2xu"}

124+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"lo bas"}}]},"finish_reason":null}],"obfuscation":"nPUTxAj3rtCV"}

125

86− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"s"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"}

126+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"h' >"}}]},"finish_reason":null}],"obfuscation":"q5MfofSUYksG0q"}

127

88− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"'"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"}

128+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":" /tmp"}}]},"finish_reason":null}],"obfuscation":"wKffSWOhi4U1l"}

129

90− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

130+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"/crush"}}]},"finish_reason":null}],"obfuscation":"hnWVxw2UITyu"}

131

92− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VuJgQMERrWZeY"}

132+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"-tes"}}]},"finish_reason":null}],"obfuscation":"yNIRDWmnBj1YMP"}

133

94− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rHTrGpoWNXByP"}

134+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"t/Tes"}}]},"finish_reason":null}],"obfuscation":"UyySVnBHPx8uK"}

135

96− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"'"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}

136+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"tCoder"}}]},"finish_reason":null}],"obfuscation":"dfH5PBYpACte"}

137

98− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" >"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

138+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"Agen"}}]},"finish_reason":null}],"obfuscation":"FlfTC0IjDo7wpx"}

139

100− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"90jo15dty52v2"}

140+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"t/ope"}}]},"finish_reason":null}],"obfuscation":"yleGcKRQfBkYk"}

101

141

102− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KOIdfkOajVkSF0"}

142+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"nai-gp"}}]},"finish_reason":null}],"obfuscation":"DJfenvE3lAfI"}

103

143

104− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"qwSqMhMyPsEED"}

144+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"t-5/"}}]},"finish_reason":null}],"obfuscation":"cu6JqV2pFk1ssl"}

105

145

106− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EfMcKDZ"}

146+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"bash_"}}]},"finish_reason":null}],"obfuscation":"kT72KQJuVjqJa"}

107

147

108− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"LH0ixU8WB3oFc"}

148+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"tool/t"}}]},"finish_reason":null}],"obfuscation":"m92wDNjF9oVM"}

109

149

110− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Create"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tqbhbSFpXlyv"}

150+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"est."}}]},"finish_reason":null}],"obfuscation":"MEagnhj45EjvGH"}

111

151

112− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yvpG9TU9mM64M"}

152+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"txt\","}}]},"finish_reason":null}],"obfuscation":"FRknPoqNFSps"}

113

153

114− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ai45EXySgETNzL"}

154+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":" \"desc"}}]},"finish_reason":null}],"obfuscation":"xySSJRkCxjS"}

115

155

116− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" with"}}]},"finish_reason":null}],"usage":null,"obfuscation":"U6jKXHjSL6ZGI"}

156+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"ript"}}]},"finish_reason":null}],"obfuscation":"beWVOpPPh4Jgxp"}

117

157

118− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" specified"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4Nck2JU9"}

158+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"ion\":"}}]},"finish_reason":null}],"obfuscation":"a2ScZYCqu4WT"}

119

159

120− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zxYeYB8DTZ"}

160+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":" \"Crea"}}]},"finish_reason":null}],"obfuscation":"YLNb1rJFheK"}

121

161

122− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VjyqfaCQB7XLD3E"}

162+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"te t"}}]},"finish_reason":null}],"obfuscation":"3y0NLCKk7pEaN3"}

123

163

124− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

164+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"est.t"}}]},"finish_reason":null}],"obfuscation":"HJbSSO2viwvUu"}

125

165

166+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"xt wit"}}]},"finish_reason":null}],"obfuscation":"NQEtsFqR9IBv"}

167+

168+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"h sp"}}]},"finish_reason":null}],"obfuscation":"jabrUA2rzh7BjC"}

169+

170+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"ecifi"}}]},"finish_reason":null}],"obfuscation":"mTiFqWOpmiEAw"}

171+

172+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"c cont"}}]},"finish_reason":null}],"obfuscation":"z2ZYFYi1piK4"}

173+

174+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"ent\""}}]},"finish_reason":null}],"obfuscation":"k1C36kkqB7dgf"}

175+

176+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"}"}}]},"finish_reason":null}],"obfuscation":"9"}

177+

178+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

179+

126− data: {"id":"chatcmpl-CQ4QjdaoWkYGTJ8CeAkKT074JMmuj","object":"chat.completion.chunk","created":1760329593,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6575,"completion_tokens":1322,"total_tokens":7897,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":1280,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"MgQGeoSgzp6CIQY"}

180+ data: {"id":"chatcmpl-CToETyeL4kJlMQdIe02g2dqGjJL0K","object":"chat.completion.chunk","created":1761220641,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6476,"completion_tokens":680,"total_tokens":7156,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"cjcP"}

127

181

128 data: [DONE]

182 data: [DONE]

129

183

@@ -132,22 +186,105 @@ interactions:

132 - text/event-stream; charset=utf-8

186 - text/event-stream; charset=utf-8

133 status: 200 OK

187 status: 200 OK

134 code: 200

188 code: 200

135− duration: 18.367812417s

189+ duration: 19.289595708s

136- id: 2

190- id: 2

137 request:

191 request:

138 proto: HTTP/1.1

192 proto: HTTP/1.1

139 proto_major: 1

193 proto_major: 1

140 proto_minor: 1

194 proto_minor: 1

141− content_length: 31052

195+ content_length: 30614

196+ host: ""

197+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_zxRiwoXvL3JbHjuK2wfHPuFs\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\\", \\\"depth\\\": 1}\",\"name\":\"ls\"},\"type\":\"function\"},{\"id\":\"call_aKrRv7qkfWJU7W8RpfGscsLN\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"printf 'hello bash' > /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/test.txt\\\", \\\"description\\\": \\\"Create test.txt with specific content\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/\\n - go.mod\\n - main.go\\n - test.txt\\n\",\"tool_call_id\":\"call_zxRiwoXvL3JbHjuK2wfHPuFs\",\"role\":\"tool\"},{\"content\":\"no output\",\"tool_call_id\":\"call_aKrRv7qkfWJU7W8RpfGscsLN\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

198+ headers:

199+ Accept:

200+ - application/json

201+ Content-Type:

202+ - application/json

203+ User-Agent:

204+ - OpenAI/Go 2.7.1

205+ url: https://api.openai.com/v1/chat/completions

206+ method: POST

207+ response:

208+ proto: HTTP/2.0

209+ proto_major: 2

210+ proto_minor: 0

211+ content_length: -1

212+ body: |+

213+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_hjkxRnPUeSqUDP1EdGWNeByg","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"5gOobPr2axxp"}

214+

215+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"yg4BpxCv7qNVdip"}

216+

217+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KGKpH0XBoRHUtm"}

218+

219+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OatPDZoPPy9uw"}

220+

221+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dMDN3Kn97lCRUOZ"}

222+

223+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6zgThxW7RKw4kjw"}

224+

225+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Dd0bHn3VGo5Fatc"}

226+

227+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N2BEN7rtkzvjKiQ"}

228+

229+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LvHXjwW7IROk5iL"}

230+

231+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ybNMH63HMHb0b"}

232+

233+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4SFAkQfj9bSa0"}

234+

235+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qkLsZWvXZn0XV"}

236+

237+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NitbZj885D35L"}

238+

239+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PnirFD29ot5Kt"}

240+

241+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

242+

243+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

244+

245+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

246+

247+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}

248+

249+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"}

250+

251+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gWcZK8V9NxE4P"}

252+

253+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TyB6lEslSe7Kw"}

254+

255+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AkF7o6evBzeh5"}

256+

257+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"09EvVghHMQG61d"}

258+

259+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VWu4rxVZ9QV3YYP"}

260+

261+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

262+

263+ data: {"id":"chatcmpl-CToEncom0cCfTCzbZlfGASg971EAS","object":"chat.completion.chunk","created":1761220661,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6629,"completion_tokens":360,"total_tokens":6989,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"b"}

264+

265+ data: [DONE]

266+

267+ headers:

268+ Content-Type:

269+ - text/event-stream; charset=utf-8

270+ status: 200 OK

271+ code: 200

272+ duration: 7.354608667s

273+- id: 3

274+ request:

275+ proto: HTTP/1.1

276+ proto_major: 1

277+ proto_minor: 1

278+ content_length: 30943

142 host: ""

279 host: ""

143− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Dtaw7aR0fdx9F1BjgDKVoQZs\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"printf '%s' 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt with specified content\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_Dtaw7aR0fdx9F1BjgDKVoQZs\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

280+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_zxRiwoXvL3JbHjuK2wfHPuFs\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\\", \\\"depth\\\": 1}\",\"name\":\"ls\"},\"type\":\"function\"},{\"id\":\"call_aKrRv7qkfWJU7W8RpfGscsLN\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"printf 'hello bash' > /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/test.txt\\\", \\\"description\\\": \\\"Create test.txt with specific content\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/\\n - go.mod\\n - main.go\\n - test.txt\\n\",\"tool_call_id\":\"call_zxRiwoXvL3JbHjuK2wfHPuFs\",\"role\":\"tool\"},{\"content\":\"no output\",\"tool_call_id\":\"call_aKrRv7qkfWJU7W8RpfGscsLN\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_hjkxRnPUeSqUDP1EdGWNeByg\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/test.txt\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|hello bash\\n</file>\\n\",\"tool_call_id\":\"call_hjkxRnPUeSqUDP1EdGWNeByg\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

144 headers:

281 headers:

145 Accept:

282 Accept:

146 - application/json

283 - application/json

147 Content-Type:

284 Content-Type:

148 - application/json

285 - application/json

149 User-Agent:

286 User-Agent:

150− - OpenAI/Go 2.3.0

287+ - OpenAI/Go 2.7.1

151 url: https://api.openai.com/v1/chat/completions

288 url: https://api.openai.com/v1/chat/completions

152 method: POST

289 method: POST

153 response:

290 response:

@@ -156,13 +293,13 @@ interactions:

156 proto_minor: 0

293 proto_minor: 0

157 content_length: -1

294 content_length: -1

158 body: |+

295 body: |+

159− data: {"id":"chatcmpl-CQ4R1vw1nUeRjbSppmEfdMmcygYqd","object":"chat.completion.chunk","created":1760329611,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"lyNH2asrkw"}

296+ data: {"id":"chatcmpl-CToEuzmiPKNzYVAFsdTxnyOYEWF9J","object":"chat.completion.chunk","created":1761220668,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"Sn6qz0bMkH"}

160

297

161− data: {"id":"chatcmpl-CQ4R1vw1nUeRjbSppmEfdMmcygYqd","object":"chat.completion.chunk","created":1760329611,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"done"},"finish_reason":null}],"usage":null,"obfuscation":"Vsu3vWpY"}

298+ data: {"id":"chatcmpl-CToEuzmiPKNzYVAFsdTxnyOYEWF9J","object":"chat.completion.chunk","created":1761220668,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"Bk5IMYBx"}

162

299

163− data: {"id":"chatcmpl-CQ4R1vw1nUeRjbSppmEfdMmcygYqd","object":"chat.completion.chunk","created":1760329611,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"5cfAPj"}

300+ data: {"id":"chatcmpl-CToEuzmiPKNzYVAFsdTxnyOYEWF9J","object":"chat.completion.chunk","created":1761220668,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"8xqXr9"}

164

301

165− data: {"id":"chatcmpl-CQ4R1vw1nUeRjbSppmEfdMmcygYqd","object":"chat.completion.chunk","created":1760329611,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6623,"completion_tokens":4,"total_tokens":6627,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"pamqF"}

302+ data: {"id":"chatcmpl-CToEuzmiPKNzYVAFsdTxnyOYEWF9J","object":"chat.completion.chunk","created":1761220668,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6686,"completion_tokens":4,"total_tokens":6690,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"wAiiq"}

166

303

167 data: [DONE]

304 data: [DONE]

168

305

@@ -171,4 +308,4 @@ interactions:

171 - text/event-stream; charset=utf-8

308 - text/event-stream; charset=utf-8

172 status: 200 OK

309 status: 200 OK

173 code: 200

310 code: 200

174− duration: 1.479184375s

311+ duration: 1.450261s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/download_tool.yaml+51−49

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,23 +24,25 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"FZb9soJ8NRHFZa"}

27+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"aOf6Uq2gmjjEnk"}

29− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":"Download"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"toz5o3Ok"}

29+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Downloading"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"cl9o1"}

31− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"kOwbGVxCB3Pp"}

31+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9nBRuhOZhwMk"}

33− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":" Save"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"C6FeX7Clw6b"}

33+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Saving"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0BdLlaA3m"}

35− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":" robots"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"AmJDhYhje"}

35+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"P50lp0jeWmmryd"}

37− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":".txt"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"FuJqPcbAsvoY"}

37+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"V8U0cjetBS7"}

39− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"wh9PRPM8zRY"}

39+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" from"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ChRD5xbbKK3"}

41− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"nGXnjnOD7U"}

41+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" URL"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"t8jg2RdgsEsM"}

43− data: {"id":"chatcmpl-CQ4IaUeAzZkWX2DdA3Bu8WLhI5gfN","object":"chat.completion.chunk","created":1760329088,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[],"usage":{"prompt_tokens":143,"completion_tokens":6,"total_tokens":149,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"q9M50b5nz64Oa4"}

43+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Tqupyqu7xS"}

44+

45+ data: {"id":"chatcmpl-CTntkZ4Vn1brlEnRZA94CCWZ3DLtp","object":"chat.completion.chunk","created":1761219356,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":143,"completion_tokens":7,"total_tokens":150,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"gyWGJIgsdlA1ge"}

45 data: [DONE]

47 data: [DONE]

@@ -49,22 +51,22 @@ interactions:

49 - text/event-stream; charset=utf-8

51 - text/event-stream; charset=utf-8

50 status: 200 OK

52 status: 200 OK

51 code: 200

53 code: 200

52− duration: 466.777167ms

54+ duration: 3.728080375s

53- id: 1

55- id: 1

54 request:

56 request:

55 proto: HTTP/1.1

57 proto: HTTP/1.1

56 proto_major: 1

58 proto_major: 1

57 proto_minor: 1

59 proto_minor: 1

58− content_length: 30737

60+ content_length: 29893

59 host: ""

61 host: ""

60− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

62+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

61 headers:

63 headers:

62 Accept:

64 Accept:

63 - application/json

65 - application/json

64 Content-Type:

66 Content-Type:

65 - application/json

67 - application/json

66 User-Agent:

68 User-Agent:

67− - OpenAI/Go 2.3.0

69+ - OpenAI/Go 2.7.1

68 url: https://api.openai.com/v1/chat/completions

70 url: https://api.openai.com/v1/chat/completions

69 method: POST

71 method: POST

70 response:

72 response:

@@ -73,55 +75,55 @@ interactions:

73 proto_minor: 0

75 proto_minor: 0

74 content_length: -1

76 content_length: -1

75 body: |+

77 body: |+

76− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_KhnHX9OwoXClCwFQ6Sn6nihw","type":"function","function":{"name":"download","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"fla8A9cU"}

78+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_DrHW4u4iTI0tW9Yd0T9Y3zfb","type":"function","function":{"name":"download","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"1CckjDsR"}

78− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"T8wwtFCJ1x3QMfF"}

80+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"zSWlXPvy488pkgv"}

80− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jATYnQfa7SiKrd"}

82+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CTCI5cnzJBdkJlL"}

82− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y7Qz2HYEiiTFJ"}

84+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"K2EA6iyXpIw6E"}

84− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lT1PEap0RJaWA"}

86+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1bi8sgqTlaUjP"}

86− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"robots"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZPcdbK3MoNye"}

88+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lNisILsX5pd47du"}

88− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QBsFdso71Xmo7G"}

90+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"http"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7HYJuiNYj8sO2Q"}

90− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"SVOUlNt2VvfkH"}

92+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"bin"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HfVkM35kmNLwVu2"}

92− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IeZEZ3IjUVdUeG4"}

94+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".org"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sz3kT9TFTkIFXV"}

94− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mzI3QI6LSQITt"}

96+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"}

96− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"h9r0QKUV0dBvk"}

98+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"robots"}}]},"finish_reason":null}],"usage":null,"obfuscation":"D4MJ9bwJL4O0"}

98− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4ngodyGh2PNwGRi"}

100+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0XXrGfWRb4zX76"}

101

100− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"http"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hLKo7uS2ZbXqqx"}

102+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"qOjgoYIkEqyoP"}

101

103

102− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"bin"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Kqbys9R1dcxOb27"}

104+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wookodCliEVO4i"}

103

105

104− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".org"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OI95IRS3hCwdGr"}

106+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BQIOAxONiYbcj"}

105

107

106− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"}

108+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Sc4p9oDi9IQPj"}

107

109

108− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"robots"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qg90huglvXtr"}

110+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"robots"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dbPeDeVa5ruP"}

109

111

110− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MN8GACi2iVwODf"}

112+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KxStUP8JCHae3T"}

111

113

112− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"gduhhVfYKFxSt"}

114+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"UXiiKEEOqxR2x"}

113

115

114− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WkUYuAYXi79"}

116+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1dYuTr09ENC"}

115

117

116− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GSQ8vVJZrtvo8ib"}

118+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dX23x9icExMPVE2"}

117

119

118− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

120+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

119

121

120− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"p"}

122+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3"}

121

123

122− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

124+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

123

125

124− data: {"id":"chatcmpl-CQ4Ia2AeuUmMhfQBJMYQvTZaCweYI","object":"chat.completion.chunk","created":1760329088,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6578,"completion_tokens":295,"total_tokens":6873,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"G"}

126+ data: {"id":"chatcmpl-CTntleHvADCmRxvdNQTUUIQZLzppr","object":"chat.completion.chunk","created":1761219357,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6479,"completion_tokens":615,"total_tokens":7094,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"eXpL"}

125

127

126 data: [DONE]

128 data: [DONE]

127

129

@@ -130,7 +132,7 @@ interactions:

130 - text/event-stream; charset=utf-8

132 - text/event-stream; charset=utf-8

131 status: 200 OK

133 status: 200 OK

132 code: 200

134 code: 200

133− duration: 7.439869334s

135+ duration: 17.82585s

134- id: 2

136- id: 2

135 request:

137 request:

136 proto: HTTP/1.1

138 proto: HTTP/1.1

@@ -156,22 +158,22 @@ interactions:

156 - text/plain

158 - text/plain

157 status: 200 OK

159 status: 200 OK

158 code: 200

160 code: 200

159− duration: 1.65837525s

161+ duration: 891.455959ms

160- id: 3

162- id: 3

161 request:

163 request:

162 proto: HTTP/1.1

164 proto: HTTP/1.1

163 proto_major: 1

165 proto_major: 1

164 proto_minor: 1

166 proto_minor: 1

165− content_length: 31171

167+ content_length: 30327

166 host: ""

168 host: ""

167− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_KhnHX9OwoXClCwFQ6Sn6nihw\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"robots.txt\\\",\\\"url\\\":\\\"https://httpbin.org/robots.txt\\\",\\\"timeout\\\":60}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool/robots.txt (Content-Type: text/plain)\",\"tool_call_id\":\"call_KhnHX9OwoXClCwFQ6Sn6nihw\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

169+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_DrHW4u4iTI0tW9Yd0T9Y3zfb\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://httpbin.org/robots.txt\\\",\\\"file_path\\\":\\\"robots.txt\\\",\\\"timeout\\\":60}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool/robots.txt (Content-Type: text/plain)\",\"tool_call_id\":\"call_DrHW4u4iTI0tW9Yd0T9Y3zfb\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

168 headers:

170 headers:

169 Accept:

171 Accept:

170 - application/json

172 - application/json

171 Content-Type:

173 Content-Type:

172 - application/json

174 - application/json

173 User-Agent:

175 User-Agent:

174− - OpenAI/Go 2.3.0

176+ - OpenAI/Go 2.7.1

175 url: https://api.openai.com/v1/chat/completions

177 url: https://api.openai.com/v1/chat/completions

176 method: POST

178 method: POST

177 response:

179 response:

@@ -180,13 +182,13 @@ interactions:

180 proto_minor: 0

182 proto_minor: 0

181 content_length: -1

183 content_length: -1

182 body: |+

184 body: |+

183− data: {"id":"chatcmpl-CQ4IkUXXua5KYaJro83H5Bj0LuMRq","object":"chat.completion.chunk","created":1760329098,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"JJZX9P7RZN"}

185+ data: {"id":"chatcmpl-CTnu3wbd4gnfJOtCvqtc3zfwgoONC","object":"chat.completion.chunk","created":1761219375,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"lGdopePQNk"}

184

186

185− data: {"id":"chatcmpl-CQ4IkUXXua5KYaJro83H5Bj0LuMRq","object":"chat.completion.chunk","created":1760329098,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"done"},"finish_reason":null}],"usage":null,"obfuscation":"CAo7gjCj"}

187+ data: {"id":"chatcmpl-CTnu3wbd4gnfJOtCvqtc3zfwgoONC","object":"chat.completion.chunk","created":1761219375,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"E4Ktb7T5"}

186

188

187− data: {"id":"chatcmpl-CQ4IkUXXua5KYaJro83H5Bj0LuMRq","object":"chat.completion.chunk","created":1760329098,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"gsviFi"}

189+ data: {"id":"chatcmpl-CTnu3wbd4gnfJOtCvqtc3zfwgoONC","object":"chat.completion.chunk","created":1761219375,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"TRfp8S"}

188

190

189− data: {"id":"chatcmpl-CQ4IkUXXua5KYaJro83H5Bj0LuMRq","object":"chat.completion.chunk","created":1760329098,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6653,"completion_tokens":4,"total_tokens":6657,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"MLGXi"}

191+ data: {"id":"chatcmpl-CTnu3wbd4gnfJOtCvqtc3zfwgoONC","object":"chat.completion.chunk","created":1761219375,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6554,"completion_tokens":4,"total_tokens":6558,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"U2M1W"}

190

192

191 data: [DONE]

193 data: [DONE]

192

194

@@ -195,4 +197,4 @@ interactions:

195 - text/event-stream; charset=utf-8

197 - text/event-stream; charset=utf-8

196 status: 200 OK

198 status: 200 OK

197 code: 200

199 code: 200

198− duration: 1.095648916s

200+ duration: 1.783744625s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/fetch_tool.yaml+51−55

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,39 +24,35 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ixlQJhRwDsHgur"}

27+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"N1lf6hhTgWgraH"}

29− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Check"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ke9PoMCYMCc"}

29+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Check"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QlFpSQXF83E"}

31− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" if"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HFdBW3iWkuQRa"}

31+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VdyxIkF4osMS"}

33− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"fAofQi3S2EoBwd"}

33+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QUoalmBgvG50C9"}

35− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"H"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IiT2W6e3QNdu4kk"}

35+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"H"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"o36kMNmcnwZN4wk"}

37− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"erman"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"20AcNU0Lrl2"}

37+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"erman"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2IfWziBeSSR"}

39− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"gT1NUSipAY0nNuI"}

39+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"zhEcVq5O8OkC4VZ"}

41− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" is"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Elhl74rYyGjVe"}

41+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"kGj7O6Qera58F"}

43− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"vKFS4hkAqDZpX"}

43+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" http"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9Fb5KYCHkqo"}

45− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" http"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"avBf3JAqQkc"}

45+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"bin"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"AeowYwz6rqaqP"}

47− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"bin"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"UBsXgM8V6YNbx"}

47+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":".org"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pWlTlkPKhrcL"}

49− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":".org"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LRsWu2W1LWAv"}

49+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" HTML"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"88u7AfsfnFo"}

51− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"'s"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QE9ulzbufK884p"}

51+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"bOSmAnM8"}

53− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" HTML"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Pg0c9NfoyTi"}

53+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"qOTbnuueOT"}

55− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0ZQ9Scw0"}

55+ data: {"id":"chatcmpl-CTnu51asNUryDd304s9TagDNB7Ys6","object":"chat.completion.chunk","created":1761219377,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":146,"completion_tokens":12,"total_tokens":158,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"lVSPLHmhrs20E"}

56−

57− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"9sTOTdFnLm"}

58−

59− data: {"id":"chatcmpl-CQ4IlFarADb0t82LgVh4dFz9E05Wu","object":"chat.completion.chunk","created":1760329099,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":146,"completion_tokens":14,"total_tokens":160,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"XxqVf6PhbnstX"}

61 data: [DONE]

57 data: [DONE]

@@ -65,22 +61,22 @@ interactions:

65 - text/event-stream; charset=utf-8

61 - text/event-stream; charset=utf-8

66 status: 200 OK

62 status: 200 OK

67 code: 200

63 code: 200

68− duration: 400.20325ms

64+ duration: 501.958ms

69- id: 1

65- id: 1

70 request:

66 request:

71 proto: HTTP/1.1

67 proto: HTTP/1.1

72 proto_major: 1

68 proto_major: 1

73 proto_minor: 1

69 proto_minor: 1

74− content_length: 30747

70+ content_length: 29903

75 host: ""

71 host: ""

76− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

72+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

77 headers:

73 headers:

78 Accept:

74 Accept:

79 - application/json

75 - application/json

80 Content-Type:

76 Content-Type:

81 - application/json

77 - application/json

82 User-Agent:

78 User-Agent:

83− - OpenAI/Go 2.3.0

79+ - OpenAI/Go 2.7.1

84 url: https://api.openai.com/v1/chat/completions

80 url: https://api.openai.com/v1/chat/completions

85 method: POST

81 method: POST

86 response:

82 response:

@@ -89,47 +85,47 @@ interactions:

89 proto_minor: 0

85 proto_minor: 0

90 content_length: -1

86 content_length: -1

91 body: |+

87 body: |+

92− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_IxDx6VP7hTi8NRqXIWVE4B60","type":"function","function":{"name":"fetch","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"rcYWq8BqVS3"}

88+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_6Mnl4lmzFlyldXYs2OrNtOtS","type":"function","function":{"name":"fetch","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"CTtY5B3pLEv"}

94− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"SmqCkGBkMG6sCzX"}

90+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"vswXZPsIvDrQ1IT"}

96− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HgeULU6BFQLK2cX"}

92+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"format"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Mrs411xnll10"}

98− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"gbFQb6PjFPAmt"}

94+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"0q8uiOYK0td3Z"}

100− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"92yUS7etdXzQm"}

96+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EUQHnBr9Cn0BYz"}

101

102− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OSJjQVw3gGxcCNW"}

98+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"46KFb2Biwhk10"}

103

104− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"http"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oyqG5m5DcPSMbG"}

100+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PfW9L7mpZyUw8U4"}

105

101

106− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"bin"}}]},"finish_reason":null}],"usage":null,"obfuscation":"k0vY1XMQzp14KgL"}

102+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"npWMxeQ1HnMf0"}

107

103

108− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".org"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b0fB8eJlH9FGLj"}

104+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7WkSFvbwDV7gf"}

109

105

110− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/html"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qIL8hrbyGHZy3"}

106+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1YY1g43jeDmNLdr"}

111

107

112− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"M0T29rINSC4Dm"}

108+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"http"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SrD1E7pK58U8WK"}

113

109

114− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"format"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EjhXHe7WuDFZ"}

110+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"bin"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bnGirbE4Ln8uzCO"}

115

111

116− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ELjP2GuirOFqK"}

112+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".org"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KPuSDoOJylAWh0"}

117

113

118− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NVSR9xLzpMUBw7"}

114+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/html"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Zkwg41erwdxlG"}

119

115

120− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"M2VpDua10HAH1"}

116+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"18e5GIH984hC7"}

121

117

122− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EfmUvigSTzV"}

118+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PF9nZDYGLX9"}

123

119

124− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pJVChWXLO5QgxSE"}

120+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SHTd44TfDRHXdqD"}

125

121

126− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"30"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

122+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"30"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

127

123

128− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"}

124+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"}

129

125

130− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

126+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

131

127

132− data: {"id":"chatcmpl-CQ4IlltLEHxQNH9CrXR2YJbImN8nR","object":"chat.completion.chunk","created":1760329099,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6583,"completion_tokens":227,"total_tokens":6810,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"m"}

128+ data: {"id":"chatcmpl-CTnu5tkhy5kQi4B5syO24gTghGWqB","object":"chat.completion.chunk","created":1761219377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6484,"completion_tokens":163,"total_tokens":6647,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"yp2G"}

133

129

134 data: [DONE]

130 data: [DONE]

135

131

@@ -138,7 +134,7 @@ interactions:

138 - text/event-stream; charset=utf-8

134 - text/event-stream; charset=utf-8

139 status: 200 OK

135 status: 200 OK

140 code: 200

136 code: 200

141− duration: 7.113165167s

137+ duration: 5.094267584s

142- id: 2

138- id: 2

143 request:

139 request:

144 proto: HTTP/1.1

140 proto: HTTP/1.1

@@ -176,22 +172,22 @@ interactions:

176 - text/html; charset=utf-8

172 - text/html; charset=utf-8

177 status: 200 OK

173 status: 200 OK

178 code: 200

174 code: 200

179− duration: 1.096670708s

175+ duration: 294.819083ms

180- id: 3

176- id: 3

181 request:

177 request:

182 proto: HTTP/1.1

178 proto: HTTP/1.1

183 proto_major: 1

179 proto_major: 1

184 proto_minor: 1

180 proto_minor: 1

185− content_length: 34628

181+ content_length: 33784

186 host: ""

182 host: ""

187− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_IxDx6VP7hTi8NRqXIWVE4B60\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://httpbin.org/html\\\",\\\"format\\\":\\\"text\\\",\\\"timeout\\\":30}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"tool_call_id\":\"call_IxDx6VP7hTi8NRqXIWVE4B60\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

183+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_6Mnl4lmzFlyldXYs2OrNtOtS\",\"function\":{\"arguments\":\"{\\\"format\\\":\\\"text\\\",\\\"url\\\":\\\"https://httpbin.org/html\\\",\\\"timeout\\\":30}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"tool_call_id\":\"call_6Mnl4lmzFlyldXYs2OrNtOtS\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

188 headers:

184 headers:

189 Accept:

185 Accept:

190 - application/json

186 - application/json

191 Content-Type:

187 Content-Type:

192 - application/json

188 - application/json

193 User-Agent:

189 User-Agent:

194− - OpenAI/Go 2.3.0

190+ - OpenAI/Go 2.7.1

195 url: https://api.openai.com/v1/chat/completions

191 url: https://api.openai.com/v1/chat/completions

196 method: POST

192 method: POST

197 response:

193 response:

@@ -200,13 +196,13 @@ interactions:

200 proto_minor: 0

196 proto_minor: 0

201 content_length: -1

197 content_length: -1

202 body: |+

198 body: |+

203− data: {"id":"chatcmpl-CQ4ItoUKSiAGOxxcSj5oGgO8EHQNq","object":"chat.completion.chunk","created":1760329107,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"vUDhd6YSNu"}

199+ data: {"id":"chatcmpl-CTnuBpOFSdtZfTMBYANWff7I4Q1sc","object":"chat.completion.chunk","created":1761219383,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"YiuSxcF3EM"}

204

200

205− data: {"id":"chatcmpl-CQ4ItoUKSiAGOxxcSj5oGgO8EHQNq","object":"chat.completion.chunk","created":1760329107,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"true"},"finish_reason":null}],"usage":null,"obfuscation":"BjBdyUVC"}

201+ data: {"id":"chatcmpl-CTnuBpOFSdtZfTMBYANWff7I4Q1sc","object":"chat.completion.chunk","created":1761219383,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Yes"},"finish_reason":null}],"usage":null,"obfuscation":"pL5t7xP1n"}

206

202

207− data: {"id":"chatcmpl-CQ4ItoUKSiAGOxxcSj5oGgO8EHQNq","object":"chat.completion.chunk","created":1760329107,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"mmxXIh"}

203+ data: {"id":"chatcmpl-CTnuBpOFSdtZfTMBYANWff7I4Q1sc","object":"chat.completion.chunk","created":1761219383,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"EKxdlc"}

208

204

209− data: {"id":"chatcmpl-CQ4ItoUKSiAGOxxcSj5oGgO8EHQNq","object":"chat.completion.chunk","created":1760329107,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7446,"completion_tokens":138,"total_tokens":7584,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"z"}

205+ data: {"id":"chatcmpl-CTnuBpOFSdtZfTMBYANWff7I4Q1sc","object":"chat.completion.chunk","created":1761219383,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7347,"completion_tokens":202,"total_tokens":7549,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"0"}

210

206

211 data: [DONE]

207 data: [DONE]

212

208

@@ -215,4 +211,4 @@ interactions:

215 - text/event-stream; charset=utf-8

211 - text/event-stream; charset=utf-8

216 status: 200 OK

212 status: 200 OK

217 code: 200

213 code: 200

218− duration: 4.198508708s

214+ duration: 7.678597541s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/glob_tool.yaml+53−53

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,29 +24,29 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"TF5ceTsirQMLnM"}

27+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ZINmRbKBItx88K"}

29− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"BDVIn6kj4ZW"}

29+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"GAzOdW7vi2f"}

31− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Fha5C9aADdg"}

31+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"RIqOr3BFDFZ"}

33− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MwvXGBvTDtxmx"}

33+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LYuomONhKplCp"}

35− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Locate"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"RVpvwdU9s"}

35+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Locate"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"BiynOXg2z"}

37− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" ."},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sjYOZnT34A9Nho"}

37+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" ."},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"bQmLmhZB1XepFq"}

39− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sT6s8EQHKNnYX1"}

39+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"q7xuhGjBgtBOp6"}

41− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4jrHEBsTFP"}

41+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"w7PStVf5Wx"}

43− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0Wwp7DAmGVsvh"}

43+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QNOgXG8wqnxd0"}

45− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Directory"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rQ9leB"}

45+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Directory"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8UmcRU"}

47− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"HqplP0jlZZ"}

47+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"RPPosRxQ2B"}

49− data: {"id":"chatcmpl-CQ4Ix4tsNjgZ3Oc1NpQoTTUiItlTv","object":"chat.completion.chunk","created":1760329111,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":137,"completion_tokens":9,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"i9NJdEkT0ojwhm"}

49+ data: {"id":"chatcmpl-CTnuINiF4D4FjTt7vDwDkDDz3KeKX","object":"chat.completion.chunk","created":1761219390,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":137,"completion_tokens":9,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"QLXTTcbD9gawzC"}

51 data: [DONE]

@@ -55,22 +55,22 @@ interactions:

55 - text/event-stream; charset=utf-8

56 status: 200 OK

57 code: 200

58− duration: 409.249583ms

58+ duration: 502.23825ms

59- id: 1

60 request:

61 proto: HTTP/1.1

62 proto_major: 1

63 proto_minor: 1

64− content_length: 30709

64+ content_length: 29865

65 host: ""

66− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

66+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

67 headers:

68 Accept:

69 - application/json

70 Content-Type:

71 - application/json

72 User-Agent:

73− - OpenAI/Go 2.3.0

73+ - OpenAI/Go 2.7.1

74 url: https://api.openai.com/v1/chat/completions

75 method: POST

76 response:

@@ -79,23 +79,23 @@ interactions:

79 proto_minor: 0

80 content_length: -1

81 body: |+

82− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_zfelpW9t7vYBEXpW66jnI5YN","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"DbgZbh0eIQGc"}

82+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_NlGpSHFtFQbqnW8h2dSL19Pt","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"zIfgXbCfh4U0"}

84− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"qrWfR1y4BousZxF"}

84+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"RNbm5MZuFLBa8KB"}

86− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bBBaBMf3XoG"}

86+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3YQYWYHRYga"}

88− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"okW4BpkotMfqN"}

88+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"7nvDljc2ly6L1"}

90− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

90+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

92− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

92+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

94− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uYNGgCjmLBaBuSi"}

94+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2DmjGdvpZpxXd0q"}

96− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

96+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

98− data: {"id":"chatcmpl-CQ4Ixt6jvePu1sTnakkBfNHV0jtaj","object":"chat.completion.chunk","created":1760329111,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6573,"completion_tokens":87,"total_tokens":6660,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"VAt"}

98+ data: {"id":"chatcmpl-CTnuJ4tADPdvPBUvuwGIFnEeausoP","object":"chat.completion.chunk","created":1761219391,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6474,"completion_tokens":151,"total_tokens":6625,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"4Uui"}

100 data: [DONE]

101

@@ -104,22 +104,22 @@ interactions:

104 - text/event-stream; charset=utf-8

105 status: 200 OK

106 code: 200

107− duration: 4.120962417s

107+ duration: 5.2708905s

108- id: 2

109 request:

110 proto: HTTP/1.1

111 proto_major: 1

112 proto_minor: 1

113− content_length: 31003

113+ content_length: 30159

114 host: ""

115− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_zfelpW9t7vYBEXpW66jnI5YN\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool/main.go\",\"tool_call_id\":\"call_zfelpW9t7vYBEXpW66jnI5YN\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

115+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_NlGpSHFtFQbqnW8h2dSL19Pt\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool/main.go\",\"tool_call_id\":\"call_NlGpSHFtFQbqnW8h2dSL19Pt\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

116 headers:

117 Accept:

118 - application/json

119 Content-Type:

120 - application/json

121 User-Agent:

122− - OpenAI/Go 2.3.0

122+ - OpenAI/Go 2.7.1

123 url: https://api.openai.com/v1/chat/completions

124 method: POST

125 response:

@@ -128,49 +128,49 @@ interactions:

128 proto_minor: 0

129 content_length: -1

130 body: |+

131− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"puKpNLeWYR"}

131+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"gR75EkGHNa"}

132

133− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"NmiS57or7U5"}

133+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"YgTFIAYEs2F"}

134

135− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"h5BvCuQ4r"}

135+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"tsDItu5j9"}

136

137− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"j3CTrLw5J"}

137+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"qd5Komr7D"}

138

139− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"8cc5clBFW"}

139+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"qeOdrfGoa"}

140

141− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"aYf8yXG"}

141+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"FK11wZb"}

142

143− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"F7Yw3tC"}

143+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"H4yxkHK"}

144

145− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"bwvptSy"}

145+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"iEyxm8y"}

146

147− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"Xd1jD1d"}

147+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"XB1BJTi"}

148

149− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"zcxC8ra"}

149+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"icYhpVa"}

150

151− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"sZpRq9yHmf"}

151+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"Bq5imswq5D"}

152

153− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"MCnDXViz9O"}

153+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"TJdakHVWWN"}

154

155− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"SussSpTiJ0"}

155+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"2qyG4KsyUg"}

156

157− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"OgSWwtzUFEF"}

157+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"3Jw0ntWJZxY"}

158

159− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"AFRBCg3MeR9"}

159+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"93YMuBqST4n"}

160

161− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/gl"},"finish_reason":null}],"usage":null,"obfuscation":"JTS6fPU45"}

161+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/gl"},"finish_reason":null}],"usage":null,"obfuscation":"JwjLfqO2A"}

162

163− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ob"},"finish_reason":null}],"usage":null,"obfuscation":"7WD4feQoFu"}

163+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ob"},"finish_reason":null}],"usage":null,"obfuscation":"RJW7cvrTNs"}

164

165− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"7OEkiuL"}

165+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"I6IYty6"}

166

167− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"DbAo1tG"}

167+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"rNjTOUc"}

168

169− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"RGRmDipJM"}

169+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"y7P7kku0B"}

170

171− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"XuwM5x"}

171+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"2RCN7G"}

172

173− data: {"id":"chatcmpl-CQ4J2KKtARKva74yKUahCMGAPLM97","object":"chat.completion.chunk","created":1760329116,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6618,"completion_tokens":22,"total_tokens":6640,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"28SU"}

173+ data: {"id":"chatcmpl-CTnuOV5QV045mTeV2Tqm4N0cahFtB","object":"chat.completion.chunk","created":1761219396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6519,"completion_tokens":22,"total_tokens":6541,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"MJFd"}

174

175 data: [DONE]

176

@@ -179,4 +179,4 @@ interactions:

179 - text/event-stream; charset=utf-8

180 status: 200 OK

181 code: 200

182− duration: 1.518499625s

182+ duration: 970.528709ms

internal/agent/testdata/TestCoderAgent/openai-gpt-5/grep_tool.yaml+110−68

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,31 +24,31 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"3QtS6v53BDQRNQ"}

27+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"d8cnm3R89KcjQ4"}

29− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Search"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"yGtIqFl95j"}

29+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Search"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MMidAmMJVR"}

31− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"oerTsE8JdpW5"}

31+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"veKuGQhWvuUa"}

33− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"56olYEI2jTXQST"}

33+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"PcYp6bwSGEWYEh"}

35− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"package"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1XfnZq6tj"}

35+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"package"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"TPF7UZyIl"}

37− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WEEyJekBLcgc9Qu"}

37+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"azxHh76lf6XXQJr"}

39− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2aq44icp6wXNW"}

39+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"DkV7YXKOo49tI"}

41− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Lcq4GVG32Gsu0"}

41+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"czivFmU9OOtBl"}

43− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"NEm2D7sPcj"}

43+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"y1WkIlT9lY"}

45− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"fhdLR8XP5b"}

45+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"V5t4ML6mkN"}

47− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" grep"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"u19mmwRjJHC"}

47+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" grep"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"qQZyIAYguG8"}

49− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"WcAyB7ZjMl"}

49+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"m37CjVMhQt"}

51− data: {"id":"chatcmpl-CQ4J3aJkaQm2RImRdrZb5hjpbl3pc","object":"chat.completion.chunk","created":1760329117,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":10,"total_tokens":148,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"diKCOl2YLfeN5"}

51+ data: {"id":"chatcmpl-CTnuPiS42WCMn3yxVYnQGjdF11fp9","object":"chat.completion.chunk","created":1761219397,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":10,"total_tokens":148,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"oJenwvVbKE5Ps"}

53 data: [DONE]

@@ -57,22 +57,22 @@ interactions:

57 - text/event-stream; charset=utf-8

58 status: 200 OK

59 code: 200

60− duration: 434.856834ms

60+ duration: 568.274792ms

61- id: 1

62 request:

63 proto: HTTP/1.1

64 proto_major: 1

65 proto_minor: 1

66− content_length: 30707

66+ content_length: 29863

67 host: ""

68− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

68+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

69 headers:

70 Accept:

71 - application/json

72 Content-Type:

73 - application/json

74 User-Agent:

75− - OpenAI/Go 2.3.0

75+ - OpenAI/Go 2.7.1

76 url: https://api.openai.com/v1/chat/completions

77 method: POST

78 response:

@@ -81,41 +81,81 @@ interactions:

81 proto_minor: 0

82 content_length: -1

83 body: |+

84− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_tvbZNPrRCtRrMj44UW3kGENg","type":"function","function":{"name":"grep","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"tzYeKyoCZhUx"}

84+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_qGqHburh9bkOKPDNhahUudPk","type":"function","function":{"name":"grep","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"4TmhxhY0Ib6r"}

86− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"W826jOSfNBIwNhe"}

86+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"BCdOPTUvR9gmSlY"}

88− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GlKTkvgIlIy"}

88+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6O7WefsoPw3VGT"}

90− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Vwxen5uWQo9Xb"}

90+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"63fSf7i7X28ucZo"}

92− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iwLszaDVdme"}

92+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fB3himcq0XoEUS0"}

94− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"c7fyBokhSrFjr"}

94+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Azwy3YtafGytmnF"}

96− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"include"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1nWInem6nEK"}

96+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PC0warMO54RLlFZ"}

98− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"6JDKpvlmUyOEQ"}

98+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DBpiv9yvvXIeNNT"}

100− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

100+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Cdc8Xld7cLqkq"}

101

102− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

102+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tTj0VHfh0q0Ve"}

103

104− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mWtzR4yD8wmga"}

104+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AN7dJvokkF1wy"}

105

106− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"literal"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iiM79DL2njw"}

106+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XzpnnmotRVGOR"}

107

108− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b5N87VN9KnAId"}

108+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QZjGQqD59Wvh3"}

109

110− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7jD2prjTWcLyMVv"}

110+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

111

112− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"true"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IXOfmadYaEzQNG"}

112+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

113

114− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"}

114+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

115

116− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

116+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y"}

117

118− data: {"id":"chatcmpl-CQ4J46UsA0jU6k4dzYyd9ho3yhcEK","object":"chat.completion.chunk","created":1760329118,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6574,"completion_tokens":97,"total_tokens":6671,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"hWJ"}

118+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"x"}

119+

120+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"}

121+

122+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"grep"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0mKtfdx6psNt30"}

123+

124+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yLKyfkZwSkETl"}

125+

126+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"isb0aq9mzT6QT"}

127+

128+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oJiMzcKBECo"}

129+

130+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"iWSw26hjTRgfQ"}

131+

132+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FBpFBGFlRz6"}

133+

134+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"wZvYv7o0BWIeY"}

135+

136+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"include"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GriwucupO9M"}

137+

138+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"oiSvZTiegsJAm"}

139+

140+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

141+

142+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

143+

144+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"EgdXXEVzrJDZ6"}

145+

146+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"literal"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DfBfuFEuyxI"}

147+

148+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6Kyq88y3xJa9L"}

149+

150+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ypikVhLBiPx07M7"}

151+

152+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"true"}}]},"finish_reason":null}],"usage":null,"obfuscation":"km3bQibO3WajZi"}

153+

154+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"}

155+

156+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

157+

158+ data: {"id":"chatcmpl-CTnuPfUpZXaOiUmyoi5j4SGruVZ6G","object":"chat.completion.chunk","created":1761219397,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6475,"completion_tokens":309,"total_tokens":6784,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"r2t8"}

119

159

120 data: [DONE]

160 data: [DONE]

121

161

@@ -124,22 +164,22 @@ interactions:

124 - text/event-stream; charset=utf-8

164 - text/event-stream; charset=utf-8

125 status: 200 OK

165 status: 200 OK

126 code: 200

166 code: 200

127− duration: 4.252992875s

167+ duration: 8.1257235s

128- id: 2

168- id: 2

129 request:

169 request:

130 proto: HTTP/1.1

170 proto: HTTP/1.1

131 proto_major: 1

171 proto_major: 1

132 proto_minor: 1

172 proto_minor: 1

133− content_length: 31091

173+ content_length: 30322

134 host: ""

174 host: ""

135− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_tvbZNPrRCtRrMj44UW3kGENg\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"package\\\",\\\"include\\\":\\\"*.go\\\",\\\"literal_text\\\":true}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool/main.go:\\n Line 1: package main\\n\",\"tool_call_id\":\"call_tvbZNPrRCtRrMj44UW3kGENg\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

175+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_qGqHburh9bkOKPDNhahUudPk\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\\",\\\"pattern\\\":\\\"package\\\",\\\"include\\\":\\\"*.go\\\",\\\"literal_text\\\":true}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_qGqHburh9bkOKPDNhahUudPk\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

136 headers:

176 headers:

137 Accept:

177 Accept:

138 - application/json

178 - application/json

139 Content-Type:

179 Content-Type:

140 - application/json

180 - application/json

141 User-Agent:

181 User-Agent:

142− - OpenAI/Go 2.3.0

182+ - OpenAI/Go 2.7.1

143 url: https://api.openai.com/v1/chat/completions

183 url: https://api.openai.com/v1/chat/completions

144 method: POST

184 method: POST

145 response:

185 response:

@@ -148,59 +188,61 @@ interactions:

148 proto_minor: 0

188 proto_minor: 0

149 content_length: -1

189 content_length: -1

150 body: |+

190 body: |+

151− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"ya7LOfuRMp"}

191+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"xMi7bDXSiZ"}

192+

193+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"nfdvyi4Zl47"}

152

194

153− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"bSaj3pO4bvL"}

195+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"cwuFIAQyQ"}

154

196

155− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"kyxGtqLYC"}

197+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"x0XiRakN8"}

156

198

157− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"2IohVxVT7"}

199+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"5UwSso4gr"}

158

200

159− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"nZB0oBqKS"}

201+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"JVHLXGH"}

160

202

161− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"VDDLvsG"}

203+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"hsXg4Tu"}

162

204

163− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"5s6uNX3"}

205+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"Klzn3ru"}

164

206

165− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"uCtnAO7"}

207+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"1k35coD"}

166

208

167− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"8rf4Fi4"}

209+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"OaAPYfq"}

168

210

169− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"Z0WTEED"}

211+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"GIvt9mXsn7"}

170

212

171− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"oyJo0440mL"}

213+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"D4Kdj9x9LC"}

172

214

173− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"cvl8fghbff"}

215+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"R0s0LLIkGW"}

174

216

175− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"zrBVNp3GNC"}

217+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"NYpDEzRBu9u"}

176

218

177− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"00XsJ2thNOq"}

219+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"e2dsudPSHSy"}

178

220

179− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"tyeQAk7LmH3"}

221+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"tFLEf3q0CEL"}

180

222

181− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"28r35FztBri"}

223+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"grep"},"finish_reason":null}],"usage":null,"obfuscation":"8bxDpKkI"}

182

224

183− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"grep"},"finish_reason":null}],"usage":null,"obfuscation":"EwSmRvRw"}

225+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"Z2cArGo"}

184

226

185− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"GXe5C3p"}

227+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"D81ujGr"}

186

228

187− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"fO0Oz10"}

229+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"OaM2L9Qvs"}

188

230

189− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"fqLmRc9G7"}

231+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"F77g5lzT7ya"}

190

232

191− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"7FiNwnYPqhH"}

233+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"dsosfWfPafW"}

192

234

193− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"GYjaD3DcF5V"}

235+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"vfDTOaznIQn"}

194

236

195− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"qvGDb1avyhx"}

237+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"ArhywxjgIDW"}

196

238

197− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" package"},"finish_reason":null}],"usage":null,"obfuscation":"U7vI"}

239+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" package"},"finish_reason":null}],"usage":null,"obfuscation":"j2vj"}

198

240

199− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"KSVwAHv"}

241+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"NgZUBVt"}

200

242

201− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"Ez0qbg"}

243+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"COn5Vw"}

202

244

203− data: {"id":"chatcmpl-CQ4J8TW9KaqCjPXyng5VOOOpIkCDO","object":"chat.completion.chunk","created":1760329122,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6643,"completion_tokens":27,"total_tokens":6670,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"YhiX"}

245+ data: {"id":"chatcmpl-CTnuXkApsWyjgU4YqPGrFOknm3jF6","object":"chat.completion.chunk","created":1761219405,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6568,"completion_tokens":28,"total_tokens":6596,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"RtYb"}

204

246

205 data: [DONE]

247 data: [DONE]

206

248

@@ -209,4 +251,4 @@ interactions:

209 - text/event-stream; charset=utf-8

251 - text/event-stream; charset=utf-8

210 status: 200 OK

252 status: 200 OK

211 code: 200

253 code: 200

212− duration: 1.151951458s

254+ duration: 1.274488666s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/ls_tool.yaml+38−34

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,21 +24,25 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ss0zUm01vjI8Ix"}

27+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"tZFC45ICW7Zb5a"}

29− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Listing"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"CgEOnF5lq"}

29+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Listing"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"jFXWqSVmx"}

31− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"C4NDSH9ws1"}

31+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"zPx0lsAxdr"}

33− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"NXiqBqvhQiA"}

33+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LZxVVe0LQhr"}

35− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" ls"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"GvB4fuj5XhcWg"}

35+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"yuOdTDLD1TDbFU"}

37− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Command"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0aXg8jsg"}

37+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"ls"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"dpSE6c3ZolPut5"}

39− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"phPtRUYRaa"}

39+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QHyjjxU1VDSO0VZ"}

41− data: {"id":"chatcmpl-CQ4J9TiP7Gph5Pi9OAwItZMTqHAPy","object":"chat.completion.chunk","created":1760329123,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":135,"completion_tokens":5,"total_tokens":140,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"fB6myFRWJxpIJH"}

41+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Command"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"hUgh65Lu"}

42+

43+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"TPmpN0XDo3"}

44+

45+ data: {"id":"chatcmpl-CTnuZ2SW0SaZmoH7AiqWV4u6fgTh9","object":"chat.completion.chunk","created":1761219407,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":135,"completion_tokens":7,"total_tokens":142,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"TrHgcXEGzlYBS8"}

43 data: [DONE]

47 data: [DONE]

@@ -47,22 +51,22 @@ interactions:

47 - text/event-stream; charset=utf-8

51 - text/event-stream; charset=utf-8

48 status: 200 OK

52 status: 200 OK

49 code: 200

53 code: 200

50− duration: 526.905584ms

54+ duration: 638.803958ms

51- id: 1

55- id: 1

52 request:

56 request:

53 proto: HTTP/1.1

57 proto: HTTP/1.1

54 proto_major: 1

58 proto_major: 1

55 proto_minor: 1

59 proto_minor: 1

56− content_length: 30701

60+ content_length: 29857

57 host: ""

61 host: ""

58− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

62+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

59 headers:

63 headers:

60 Accept:

64 Accept:

61 - application/json

65 - application/json

62 Content-Type:

66 Content-Type:

63 - application/json

67 - application/json

64 User-Agent:

68 User-Agent:

65− - OpenAI/Go 2.3.0

69+ - OpenAI/Go 2.7.1

66 url: https://api.openai.com/v1/chat/completions

70 url: https://api.openai.com/v1/chat/completions

67 method: POST

71 method: POST

68 response:

72 response:

@@ -71,21 +75,21 @@ interactions:

71 proto_minor: 0

75 proto_minor: 0

72 content_length: -1

76 content_length: -1

73 body: |+

77 body: |+

74− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_QYlDpgmQx1ouxLStlnk3hoJZ","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"YrAgxsiRsdYoG6"}

78+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Elf9zwpU7JL6BiwAUVM82C1z","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"Ts5sWl36Aw36xr"}

76− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hb92dZDobsPeowS"}

80+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hExulYfByjk9jWe"}

78− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cI0kNdEvUhIlfS"}

82+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5ZTtxJimxFViMy"}

80− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FLvNGECirWi1l5i"}

84+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fqFaBSl9qNBEUb7"}

82− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \".\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"byBavSbX5eRh"}

86+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \".\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"V6UWbyP33dn9"}

84− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M"}

88+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6"}

86− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

90+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

88− data: {"id":"chatcmpl-CQ4J97jXxcGqHLqFTi4gFY59nIqBq","object":"chat.completion.chunk","created":1760329123,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6571,"completion_tokens":215,"total_tokens":6786,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"t"}

92+ data: {"id":"chatcmpl-CTnuZtJMMJvm311RO10X5sEBoBBoI","object":"chat.completion.chunk","created":1761219407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6472,"completion_tokens":215,"total_tokens":6687,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"4Wmn"}

90 data: [DONE]

94 data: [DONE]

@@ -94,22 +98,22 @@ interactions:

94 - text/event-stream; charset=utf-8

98 - text/event-stream; charset=utf-8

95 status: 200 OK

99 status: 200 OK

96 code: 200

100 code: 200

97− duration: 6.854251541s

101+ duration: 7.094167958s

98- id: 2

102- id: 2

99 request:

103 request:

100 proto: HTTP/1.1

104 proto: HTTP/1.1

101 proto_major: 1

105 proto_major: 1

102 proto_minor: 1

106 proto_minor: 1

103− content_length: 31010

107+ content_length: 30166

104 host: ""

108 host: ""

105− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_QYlDpgmQx1ouxLStlnk3hoJZ\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_QYlDpgmQx1ouxLStlnk3hoJZ\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

109+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Elf9zwpU7JL6BiwAUVM82C1z\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Elf9zwpU7JL6BiwAUVM82C1z\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

106 headers:

110 headers:

107 Accept:

111 Accept:

108 - application/json

112 - application/json

109 Content-Type:

113 Content-Type:

110 - application/json

114 - application/json

111 User-Agent:

115 User-Agent:

112− - OpenAI/Go 2.3.0

116+ - OpenAI/Go 2.7.1

113 url: https://api.openai.com/v1/chat/completions

117 url: https://api.openai.com/v1/chat/completions

114 method: POST

118 method: POST

115 response:

119 response:

@@ -118,21 +122,21 @@ interactions:

118 proto_minor: 0

122 proto_minor: 0

119 content_length: -1

123 content_length: -1

120 body: |+

124 body: |+

121− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"6e1hHZiomP"}

125+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"ng5JXt8d5w"}

122

126

123− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"6MekB0Kibq"}

127+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"M32vNyjKMt"}

124

128

125− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"KY64Jfn8"}

129+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"4eazwHdr"}

126

130

127− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"RmygCKmQwA"}

131+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"finish_reason":null}],"usage":null,"obfuscation":"GbRz2IIwZxW"}

128

132

129− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"main"},"finish_reason":null}],"usage":null,"obfuscation":"tFGy5G2K"}

133+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"hL5IhJ1"}

130

134

131− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"oBqdcRPrY"}

135+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"5K3oomxnQ"}

132

136

133− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"lBxrVB"}

137+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"j1AUxh"}

134

138

135− data: {"id":"chatcmpl-CQ4JHcicfV6chAE46sE4Mt6pNAAMg","object":"chat.completion.chunk","created":1760329131,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6628,"completion_tokens":8,"total_tokens":6636,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"AINpb"}

139+ data: {"id":"chatcmpl-CTnugI4UtWkVJf1hMoD7JIcEzUhfM","object":"chat.completion.chunk","created":1761219414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6529,"completion_tokens":8,"total_tokens":6537,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"x7eIs"}

136

140

137 data: [DONE]

141 data: [DONE]

138

142

@@ -141,4 +145,4 @@ interactions:

141 - text/event-stream; charset=utf-8

145 - text/event-stream; charset=utf-8

142 status: 200 OK

146 status: 200 OK

143 code: 200

147 code: 200

144− duration: 1.683196417s

148+ duration: 971.224792ms

internal/agent/testdata/TestCoderAgent/openai-gpt-5/multiedit_tool.yaml+371−204

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,29 +24,29 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HRyvw6HF603W2p"}

27+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"G1vYR2Yb0RBwDS"}

29− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Modify"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Im99UEtqsk"}

29+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Edit"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ReCqcIFdlgeB"}

31− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Greeting"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"I1Qilv1"}

31+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8bZtr3W7Er"}

33− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Text"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"nc2WYiSAHa4"}

33+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Message"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0WwcqvRj"}

35− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"T9lMveFuBpOi"}

35+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"v8qseZ3ccGJk"}

37− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Add"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QkKwqKxEvxu4"}

37+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Add"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1wO46M3JOP5N"}

39− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Comment"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2MK1jAdh"}

39+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Comment"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IrNKj1yT"}

41− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"e1VsQhHkvNaVu"}

41+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"r1GqEBxGY6esY"}

43− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"m3z52chYs5e"}

43+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HJm3ej2BlEz"}

45− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"EXKWupnwwEn5h"}

45+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OtXfMAJLLej2y"}

47− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"o4Chrs6lUT"}

47+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"8NMqR5O0Ut"}

49− data: {"id":"chatcmpl-CQ4JIzmq20xYtHRivxxGjnzXA3uj7","object":"chat.completion.chunk","created":1760329132,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":157,"completion_tokens":9,"total_tokens":166,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"44gGnjfrcvYfqg"}

49+ data: {"id":"chatcmpl-CTnuhUejVhrVn7z96Ws5FlZr04xCt","object":"chat.completion.chunk","created":1761219415,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":157,"completion_tokens":9,"total_tokens":166,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"E0L1TPWsfwAEhV"}

51 data: [DONE]

@@ -55,22 +55,22 @@ interactions:

55 - text/event-stream; charset=utf-8

56 status: 200 OK

57 code: 200

58− duration: 447.762542ms

58+ duration: 459.876666ms

59- id: 1

60 request:

61 proto: HTTP/1.1

62 proto_major: 1

63 proto_minor: 1

64− content_length: 30787

64+ content_length: 29943

65 host: ""

66− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

66+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

67 headers:

68 Accept:

69 - application/json

70 Content-Type:

71 - application/json

72 User-Agent:

73− - OpenAI/Go 2.3.0

73+ - OpenAI/Go 2.7.1

74 url: https://api.openai.com/v1/chat/completions

75 method: POST

76 response:

@@ -79,31 +79,31 @@ interactions:

79 proto_minor: 0

80 content_length: -1

81 body: |+

82− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_qimzDg7DfEVY0zVw1nO0gv75","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"XkkNDuwpAyXpkm"}

82+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_I1pqDnM1TWQB4HuafXT8Nfy9","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"7J4H9megt3uMwJ"}

84− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"cyHvFcf2jVFmWeQ"}

84+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"agExJoetonDee20"}

86− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RWjUyusIFYREbS"}

86+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wHXqFNJ0dtXYQV"}

88− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w0MlhCCbeKhsTC1"}

88+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aFm2pM78O7eTXLV"}

90− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \".\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"Jt8D52aQwdd"}

90+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"rxRbuIXaQm5s"}

92− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"alIVggDgeN47nlV"}

92+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PN9YbHnMJzBua3j"}

94− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jgNZPu4tinSav"}

94+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9nlK6byWb0QIW"}

96− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"74r9TANdmDiDzwu"}

96+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PIJqFD1EmF0gQDP"}

98− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"}

98+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"n"}

100− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G"}

100+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M"}

101

102− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"}

102+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"}

103

104− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

104+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

105

106− data: {"id":"chatcmpl-CQ4JIXJg7ceTHw6jTEBxgtlK7pYBq","object":"chat.completion.chunk","created":1760329132,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6595,"completion_tokens":28,"total_tokens":6623,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"VVx6"}

106+ data: {"id":"chatcmpl-CTnuhMRKh33EPuGe3o5MAD5KOLCc9","object":"chat.completion.chunk","created":1761219415,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6496,"completion_tokens":220,"total_tokens":6716,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"5VWy"}

107

108 data: [DONE]

109

@@ -112,22 +112,22 @@ interactions:

112 - text/event-stream; charset=utf-8

113 status: 200 OK

114 code: 200

115− duration: 3.014332667s

115+ duration: 5.791229709s

116- id: 2

117 request:

118 proto: HTTP/1.1

119 proto_major: 1

120 proto_minor: 1

121− content_length: 31117

121+ content_length: 30272

122 host: ""

123− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

123+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

124 headers:

125 Accept:

126 - application/json

127 Content-Type:

128 - application/json

129 User-Agent:

130− - OpenAI/Go 2.3.0

130+ - OpenAI/Go 2.7.1

131 url: https://api.openai.com/v1/chat/completions

132 method: POST

133 response:

@@ -136,63 +136,63 @@ interactions:

136 proto_minor: 0

137 content_length: -1

138 body: |+

139− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Ra631dmm4DM6J9UnzvywosFz","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"YFlE1RtZdx9j"}

139+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_BNSQsI4vcwCJHudYZPnlzacU","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"dbsm60mUtFOJ"}

140

141− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lJzBCaPOdYstGil"}

141+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"dp0m6PpNNjrsMXL"}

142

143− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"64E99nG4vWJgYk"}

143+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jKalXmgEsGvRbx"}

144

145− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d3fPQxwtbUjJy"}

145+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AYIyH0uWhzyIW"}

146

147− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vpwNDVSI48jkdhH"}

147+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"exBiEiYtA2TV6Fy"}

148

149− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jfFRNv7MW1nuKwi"}

149+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Uf7aBMr2lvMqt6o"}

150

151− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vXmBfrMkMZku7wd"}

151+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ID38yz20p7egp0G"}

152

153− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b7lWYgF97lQ1ySy"}

153+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ndCNdUzkSbA18p0"}

154

155− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G2pgPlTkrvzUfzK"}

155+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WAXTjg4IYcSvgle"}

156

157− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Mv45sGXNgYWdT"}

157+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4sgIA8DP761WL"}

158

159− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PrVpGNz8qIAmq"}

159+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uARUJmQm6FyfX"}

160

161− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QzRins2dPVOFz"}

161+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xG70qLa2rbT0l"}

162

163− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cA8HurRUTGZbU"}

163+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0ijuC1Bxnavce"}

164

165− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V2uyZ8bd9jziw"}

165+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MvxRfqBYOZWpR"}

166

167− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

167+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

168

169− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

169+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

170

171− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

171+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

172

173− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"}

173+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"}

174

175− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"}

175+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"}

176

177− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

177+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

178

179− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"frSnWpW5xzs2F8Q"}

179+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"onGCjOvVcY00QTT"}

180

181− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tkb1GeF0EOHjObQ"}

181+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1Nvg2gUq24j9a2O"}

182

183− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

183+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

184

185− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yq0JfZ7uTjEtt"}

185+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z9lkasmPQgD5s"}

186

187− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BUTKWTLRox6KB"}

187+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nAT6xRBE1GEHl"}

188

189− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vKcRQ1sF4GzYlcY"}

189+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d7oi3J4NsdZDyCv"}

190

191− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WhYCG9TudBxlHIV"}

191+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UcMBGGBTBOkLJ6a"}

192

193− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

193+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

194

195− data: {"id":"chatcmpl-CQ4JLlsyt6qNkY7eJxlkRvtapMGEr","object":"chat.completion.chunk","created":1760329135,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6658,"completion_tokens":37,"total_tokens":6695,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ckIKUrr"}

195+ data: {"id":"chatcmpl-CTnunS0yO8jAM3EPGelBeSUbFLY5c","object":"chat.completion.chunk","created":1761219421,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6557,"completion_tokens":37,"total_tokens":6594,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"F2kO"}

196

197 data: [DONE]

198

@@ -201,22 +201,22 @@ interactions:

201 - text/event-stream; charset=utf-8

202 status: 200 OK

203 code: 200

204− duration: 1.47161875s

204+ duration: 1.339392458s

205- id: 3

206 request:

207 proto: HTTP/1.1

208 proto_major: 1

209 proto_minor: 1

210− content_length: 31566

210+ content_length: 30721

211 host: ""

212− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_Ra631dmm4DM6J9UnzvywosFz\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_Ra631dmm4DM6J9UnzvywosFz\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

212+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

213 headers:

214 Accept:

215 - application/json

216 Content-Type:

217 - application/json

218 User-Agent:

219− - OpenAI/Go 2.3.0

219+ - OpenAI/Go 2.7.1

220 url: https://api.openai.com/v1/chat/completions

221 method: POST

222 response:

@@ -225,193 +225,249 @@ interactions:

225 proto_minor: 0

226 content_length: -1

227 body: |+

228− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Ley8oJ1VgDmAILKbCpu5dICh","type":"function","function":{"name":"multiedit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"5qtmWK5"}

228+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_a4kxZbiotTZsM3aIqLs1TIYS","type":"function","function":{"name":"multiedit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"izjgR2y"}

229

230− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"cHIJSvUKz1V9IfY"}

230+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"yaARuOQM6NWeQgZ"}

231

232− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iIehSSh4DEV2rc"}

232+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mH3KAOKWNaYSQc"}

233

234− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nqBasfFS4lz6A"}

234+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f6R97GaACwluc"}

235

236− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wyLuHKf9Uhsg3oO"}

236+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JmYrBmC1sUnEINf"}

237

238− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4lsxT43K8rCCbQF"}

238+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"quumMPs9jcWXqg1"}

239

240− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5MMoE3l1FSBIODA"}

240+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WApqdQnmqdRMW1Q"}

241

242− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5byQDgcXYJVlqwI"}

242+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KCCVoxyo3c2h0J0"}

243

244− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8BpvQeZQ56ZSpR1"}

244+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Tqoc98epwFahUQT"}

245

246− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wqFjajW0mIV9m"}

246+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qZSa7LaFnMgeu"}

247

248− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TJb4nzQFXEk1D"}

248+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q5zI7HALAIDUA"}

249

250− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FfPr9DpsmZrto"}

250+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sEFeeMoUyz8DQ"}

251

252− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BHfhnG7PNlsJO"}

252+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lcamp73Q7gYzB"}

253

254− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2G23nw7PoPcFY"}

254+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BsPq1DCU73M8g"}

255

256− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

256+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

257

258− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

258+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

259

260− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

260+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

261

262− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"W"}

262+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"i"}

263

264− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3"}

264+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H"}

265

266− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

266+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

267

268− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qJzoZw1CNb311LT"}

268+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ElHVM5gv0ssnKpR"}

269

270− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JtVzv0RT0IXRZWX"}

270+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"98R4m0IQAZs4I6a"}

271

272− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

272+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

273

274− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VrWFcjRgeBKwI"}

274+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VvkfaGjnL42QU"}

275

276− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"93ARxjOesj5M9"}

276+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jMeA3QAnBHcho"}

277

278− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BTThrRHa2hNM8cr"}

278+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bkTFtweKkHBTkFI"}

279

280− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"JyAIcmAbEPvJF"}

280+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"YjJHnr8dynyI8"}

281

282− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ed"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

282+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ed"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

283

284− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"its"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V3GO8MZkHTJPhMr"}

284+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"its"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dP1ggR0cgBj84EB"}

285

286− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":["}}]},"finish_reason":null}],"usage":null,"obfuscation":"bb191of79i3OIV"}

286+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":["}}]},"finish_reason":null}],"usage":null,"obfuscation":"99vEOKbZAK7zVW"}

287

288− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"CXB6zDznwstW9vG"}

288+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"MUcBp8T8bKD5aBE"}

289

290− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TTzioeZaThxXbqq"}

290+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kqcpJ8kcYMxnA5u"}

291

292− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RICXAEue4m7"}

292+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dZyiOdQxLuU"}

293

294− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"6dK4lREjsZFJ1"}

294+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"m98cvO7QBaobv"}

295

296− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

296+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G7yLCHGQmVuHIA"}

297

298− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

298+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3LlECcYNTKHMy"}

299

300− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

300+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

301

302− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HADAGZYmm5"}

302+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mNP35pebZrxFpH"}

303

304− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"XZ27MIpzcwgpO"}

304+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0"}

305

306− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LoL0lGayq4KTv"}

306+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"66F6CpR0YlI16ac"}

307

308− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}

308+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LPCQFvZV9sffAnu"}

309

310− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V8BmOt9SFlos"}

310+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DzeotZIuh7"}

311

312− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UJzUcVKl77rIynH"}

312+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"L2BVPRo08ProR"}

313

314− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yy1pc57uGXNCjf2"}

314+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P6m4FlTaC0KWc"}

315

316− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"M7a0xAcI0BzrW"}

316+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"0"}

317

318− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LS5XxhTGnP6vTiR"}

318+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KkyygJPhQBYT"}

319

320− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PxI6XMkVxpC"}

320+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AlTLdC2jBrdLfNP"}

321

322− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"yz2INbnBF4ekB"}

322+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tBzz6EWT2PpgtoC"}

323

324− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

324+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

325

326− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

326+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"}

327

328− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

328+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b"}

329

330− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d6JwTvK3xJ"}

330+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"nlpp0dY78lADR"}

331

332− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mASdYirG3EUyL"}

332+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2njlOwSBznngN7N"}

333

334− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Dl70WtMU2FySq"}

334+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vY60Cc6V6Br"}

335

336− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"N"}

336+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"V5UPty5nk2xVn"}

337

338− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CqUJBztB0jWR"}

338+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Gkp9ElzkENIm9f"}

339

340− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3hq4Vk8Rn3F15Wn"}

340+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1TtmoXY1NuHUU"}

341

342− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QW3P6kFmYpEtTzN"}

342+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

343

344− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"},{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"SoIrgzpVp6X"}

344+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r2dZZVgPdu1VVF"}

345

346− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cWjoPPr1a59s63E"}

346+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7"}

347

348− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q9E6gIKhVfr"}

348+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"owrNqr27VkLremw"}

349

350− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"86gpJtXt6u8gf"}

350+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OifhxnUUtmVOTHo"}

351

352− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

352+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"72v4kEQnU0"}

353

354− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

354+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"6oLkjnbwagbGz"}

355

356− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

356+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7zNgikeJLR0Q9"}

357

358− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8GePe6fl5s"}

358+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"3"}

359

360− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"uT0Jy23arR3Y0"}

360+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ufeiG6itlvX8"}

361

362− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RYuQ9Mjyy8J88"}

362+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mxmRiBKmr6l1HXq"}

363

364− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"}

364+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q9CPtiUdcbQe7XY"}

365

366− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4xukq53BtWwL"}

366+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

367

368− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kCdO4YoD4h4tz3l"}

368+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8"}

369

370− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8wz0iWo2yqB1qoA"}

370+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"9KXJdjNQTY3gY3D"}

371

372− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lrOZAGAdkmDv7"}

372+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"},{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"87bTlegiPI4DK"}

373

374− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G5hkvSlqLghjrWF"}

374+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c3zJQKjWDBFhoX6"}

375

376− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6S1YKz4DKsY"}

376+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mnjvLwI3gyf"}

377

378− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"54FIKK1nBegv5"}

378+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"DBKyC8QGxoq5o"}

379

380− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

380+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"E4LXfTr2hjbpWZ"}

381

382− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}

382+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kLwq8fAnA1Nhl"}

383

384− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"//"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

384+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

385

386− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Greeting"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wNQs69rdI"}

386+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"97wNbZbA9agddm"}

387

388− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7zmkNAKKjnjXn1Z"}

388+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"}

389

390− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ytbN9PFPlgy2FeL"}

390+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qZMxMpZ7do6AiQt"}

391

392− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wlIAxmLIzrAOxKl"}

392+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"34T2nFrItljqUnZ"}

393

394− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PaXTUcH8Lt"}

394+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zh6hMLHfUA"}

395

396− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"uztrOOm1nKvgW"}

396+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"69YJeEI2nT9do"}

397

398− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y65s2d69Tqdpr"}

398+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZN0nhEU2WpRRY"}

399

400− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"9"}

400+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"i"}

401

402− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oVbylVLOFg3Q"}

402+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NHUfcyL2D6cX"}

403

404− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JCAbq5Rt1MBseN7"}

404+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CUzwXu64jvLhCJs"}

405

406− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7gWnVZNup92RZ7L"}

406+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tW0206RJGvODZei"}

407

408− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QSH8kiGhfd86a45"}

408+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

409

410− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"]}"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

410+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0"}

411

412− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

412+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9"}

413

414− data: {"id":"chatcmpl-CQ4JNwZMuxI045y2nHzEf83UYfnvn","object":"chat.completion.chunk","created":1760329137,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6757,"completion_tokens":1326,"total_tokens":8083,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":1216,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"bUR5KjnusD4Ao6A"}

414+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ngj1KzyLwnuSQ"}

415+

416+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iUhhpvj1bheLeKY"}

417+

418+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uOHi3CfQJen"}

419+

420+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"NQnF7ZTz5x3rI"}

421+

422+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2aQU9D20In1R9c"}

423+

424+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zIGCopFyn8Tgm"}

425+

426+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

427+

428+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IarDaoFM0SOYK0"}

429+

430+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z"}

431+

432+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1VTaWOaAIonN25V"}

433+

434+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"//"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

435+

436+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Greeting"}}]},"finish_reason":null}],"usage":null,"obfuscation":"De6oXIcQN"}

437+

438+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sNAKfNIc8Lt3CEc"}

439+

440+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4tPosXcadbMkKVM"}

441+

442+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y5okD5mRDbHJL0m"}

443+

444+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rm5ROq5rmm"}

445+

446+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"y0LMLC3pkHSc3"}

447+

448+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C2giZxA0RlmZf"}

449+

450+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"X"}

451+

452+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PEZiylW5fnnV"}

453+

454+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z8wBTBnRHFd0f9u"}

455+

456+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"84wHeBUYFcgcX1W"}

457+

458+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

459+

460+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"v"}

461+

462+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"x"}

463+

464+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4oCwpJAFsgx8SNm"}

465+

466+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"]}"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

467+

468+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

469+

470+ data: {"id":"chatcmpl-CTnuo6FCRWAESNG10XxFx9qruu9rn","object":"chat.completion.chunk","created":1761219422,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6656,"completion_tokens":2442,"total_tokens":9098,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":2304,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"SSipCwL4b0cgihe"}

415

471

416 data: [DONE]

472 data: [DONE]

417

473

@@ -420,22 +476,22 @@ interactions:

420 - text/event-stream; charset=utf-8

476 - text/event-stream; charset=utf-8

421 status: 200 OK

477 status: 200 OK

422 code: 200

478 code: 200

423− duration: 22.325641334s

479+ duration: 37.907893209s

424- id: 4

480- id: 4

425 request:

481 request:

426 proto: HTTP/1.1

482 proto: HTTP/1.1

427 proto_major: 1

483 proto_major: 1

428 proto_minor: 1

484 proto_minor: 1

429− content_length: 32243

485+ content_length: 31478

430 host: ""

486 host: ""

431− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_Ra631dmm4DM6J9UnzvywosFz\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_Ra631dmm4DM6J9UnzvywosFz\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_Ley8oJ1VgDmAILKbCpu5dICh\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"},{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_Ley8oJ1VgDmAILKbCpu5dICh\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

487+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_a4kxZbiotTZsM3aIqLs1TIYS\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"},{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_a4kxZbiotTZsM3aIqLs1TIYS\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

432 headers:

488 headers:

433 Accept:

489 Accept:

434 - application/json

490 - application/json

435 Content-Type:

491 Content-Type:

436 - application/json

492 - application/json

437 User-Agent:

493 User-Agent:

438− - OpenAI/Go 2.3.0

494+ - OpenAI/Go 2.7.1

439 url: https://api.openai.com/v1/chat/completions

495 url: https://api.openai.com/v1/chat/completions

440 method: POST

496 method: POST

441 response:

497 response:

@@ -444,63 +500,63 @@ interactions:

444 proto_minor: 0

500 proto_minor: 0

445 content_length: -1

501 content_length: -1

446 body: |+

502 body: |+

447− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_fCHMtOuF9dZZtCqpYij5lyc1","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"vCOXFQJMTepK"}

503+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_MAOXFW9Z1yjTHrVUbwrhdgDZ","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"RkWyYD0uRWRe"}

448

504

449− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"FnueHYsRXMCoahd"}

505+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ng4Pe9e5fsmFbN2"}

450

506

451− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qBTVberzU6oxH3"}

507+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nJxVtEurm9PD4C"}

452

508

453− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bQTi1UmtWCMmY"}

509+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jcOsoKEN5d9cT"}

454

510

455− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tlXYkAIYcjEXW7U"}

511+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qikXdZb16VqqFQT"}

456

512

457− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ei26OthiyNXWLvK"}

513+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YvWR8iyWMJ0nTAA"}

458

514

459− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XZ5SeMiVIgQEzcx"}

515+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1P4fW3CDfanggsH"}

460

516

461− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KB2gYWQNg0ty0qW"}

517+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7nZp2OXz0BiD1G7"}

462

518

463− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c0oaw3dJDahrXwy"}

519+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ALTgAH0BrA8Z0mE"}

464

520

465− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lv8f6Ws4SsFOc"}

521+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gGXn6zbFBAonW"}

466

522

467− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"g7oMHWL3BetbA"}

523+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rcS6qmaK9QmNP"}

468

524

469− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zBPhdbVMesEf0"}

525+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yV5Hlc7jH12ps"}

470

526

471− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B7xfAWg4Mx8A8"}

527+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QINY6qVFpkItV"}

472

528

473− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Wjt3K3SEJwsGR"}

529+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TnudXocP7gGtU"}

474

530

475− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

531+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

476

532

477− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

533+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

478

534

479− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

535+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

480

536

481− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"U"}

537+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H"}

482

538

483− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"S"}

539+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"}

484

540

485− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

541+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

486

542

487− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z45Uvo63pkWAh6n"}

543+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4KTumxiI3fbmcMm"}

488

544

489− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"prcKv5iswzFJIEl"}

545+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Rc8yCLRkUv6cDDS"}

490

546

491− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

547+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

492

548

493− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lL8LIaqTGlp5t"}

549+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kCSQqiEXhiwFy"}

494

550

495− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fOjokSZqSD5kv"}

551+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yAuSto5lEh9j8"}

496

552

497− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RQ7nNPP4iam8Hdd"}

553+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5niLgnxuyOpu67t"}

498

554

499− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9KYNLG611aZAJUq"}

555+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ix1bU5RP1zuarzD"}

500

556

501− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

557+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

502

558

503− data: {"id":"chatcmpl-CQ4Jk3FeiJRA0Om5lkhmvwQBhBrEP","object":"chat.completion.chunk","created":1760329160,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6908,"completion_tokens":37,"total_tokens":6945,"prompt_tokens_details":{"cached_tokens":6656,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"qGR9"}

559+ data: {"id":"chatcmpl-CTnvRqybvooZg3pHL0ZJn4DEafuRl","object":"chat.completion.chunk","created":1761219461,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6835,"completion_tokens":37,"total_tokens":6872,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"6xao"}

504

560

505 data: [DONE]

561 data: [DONE]

506

562

@@ -509,22 +565,22 @@ interactions:

509 - text/event-stream; charset=utf-8

565 - text/event-stream; charset=utf-8

510 status: 200 OK

566 status: 200 OK

511 code: 200

567 code: 200

512− duration: 1.043466542s

568+ duration: 2.4844135s

513- id: 5

569- id: 5

514 request:

570 request:

515 proto: HTTP/1.1

571 proto: HTTP/1.1

516 proto_major: 1

572 proto_major: 1

517 proto_minor: 1

573 proto_minor: 1

518− content_length: 32714

574+ content_length: 31949

519 host: ""

575 host: ""

520− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_qimzDg7DfEVY0zVw1nO0gv75\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_Ra631dmm4DM6J9UnzvywosFz\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_Ra631dmm4DM6J9UnzvywosFz\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_Ley8oJ1VgDmAILKbCpu5dICh\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"},{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_Ley8oJ1VgDmAILKbCpu5dICh\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_fCHMtOuF9dZZtCqpYij5lyc1\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\t// Greeting\\n 7|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 8|}\\n</file>\\n\",\"tool_call_id\":\"call_fCHMtOuF9dZZtCqpYij5lyc1\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

576+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_a4kxZbiotTZsM3aIqLs1TIYS\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"},{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_a4kxZbiotTZsM3aIqLs1TIYS\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_MAOXFW9Z1yjTHrVUbwrhdgDZ\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\t// Greeting\\n 7|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 8|}\\n</file>\\n\",\"tool_call_id\":\"call_MAOXFW9Z1yjTHrVUbwrhdgDZ\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

521 headers:

577 headers:

522 Accept:

578 Accept:

523 - application/json

579 - application/json

524 Content-Type:

580 Content-Type:

525 - application/json

581 - application/json

526 User-Agent:

582 User-Agent:

527− - OpenAI/Go 2.3.0

583+ - OpenAI/Go 2.7.1

528 url: https://api.openai.com/v1/chat/completions

584 url: https://api.openai.com/v1/chat/completions

529 method: POST

585 method: POST

530 response:

586 response:

@@ -533,15 +589,126 @@ interactions:

533 proto_minor: 0

589 proto_minor: 0

534 content_length: -1

590 content_length: -1

535 body: |+

591 body: |+

536− data: {"id":"chatcmpl-CQ4JlEVVZuky9TcnyG7DP5xRewT7E","object":"chat.completion.chunk","created":1760329161,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"o99ljdA9x8"}

592+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Q0CkA8QSKRIzRVl4xl37sxzS","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"fx9kYN2x64Uo"}

593+

594+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tTW88Muso6gMNbw"}

595+

596+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YhzEPx5747e"}

597+

598+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"UOMNX7tpDzEsl"}

599+

600+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

601+

602+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N16w911BlQvKTE"}

603+

604+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

605+

606+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uRIoJWAwpaK7osU"}

607+

608+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AAhGrB9GLNURy3k"}

609+

610+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PTbKfSA5flUkZCe"}

611+

612+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IPQ3NxfiCpti0"}

613+

614+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DW4468SgFRxcX"}

615+

616+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7COTDS4X2u2tr"}

617+

618+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iO1MVsLQS31cF"}

619+

620+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YUPLT6sppw8YN"}

621+

622+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

623+

624+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

625+

626+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

627+

628+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"k"}

629+

630+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"}

537

631

538− data: {"id":"chatcmpl-CQ4JlEVVZuky9TcnyG7DP5xRewT7E","object":"chat.completion.chunk","created":1760329161,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"f5cwiTX7"}

632+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

633+

634+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JF1HuvPj8PmjgoJ"}

635+

636+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QmWeo7c46B48GqT"}

637+

638+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

639+

640+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ER25C2CHZbh7f"}

641+

642+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"guua4msWWuEa5"}

643+

644+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zViBQMknb5012pr"}

645+

646+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"kSK9Gkg9aGvAn"}

647+

648+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n24IPQn"}

649+

650+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"HcMkw1iVjqZaI"}

651+

652+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IXAGUJGpEksF5lY"}

653+

654+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jNwrIar7EPLt8b"}

655+

656+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bzRjRtbuHS9bQOo"}

657+

658+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" program"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ICSINrZSmU"}

659+

660+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" to"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fiKA0x0NPv6RXFN"}

661+

662+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IJf9UKytcg86N"}

663+

664+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fBUCwLAfnjqaoZ"}

665+

666+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" output"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Oxymj186SMV"}

667+

668+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7qbzMcEIRdCP1JE"}

669+

670+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

671+

672+ data: {"id":"chatcmpl-CTnvTcFkCzIJS6b3vSpmYhvZs1Fzx","object":"chat.completion.chunk","created":1761219463,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6942,"completion_tokens":50,"total_tokens":6992,"prompt_tokens_details":{"cached_tokens":6784,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"pjzW"}

673+

674+ data: [DONE]

675+

676+ headers:

677+ Content-Type:

678+ - text/event-stream; charset=utf-8

679+ status: 200 OK

680+ code: 200

681+ duration: 2.076505458s

682+- id: 6

683+ request:

684+ proto: HTTP/1.1

685+ proto_major: 1

686+ proto_minor: 1

687+ content_length: 32397

688+ host: ""

689+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_I1pqDnM1TWQB4HuafXT8Nfy9\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_BNSQsI4vcwCJHudYZPnlzacU\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_a4kxZbiotTZsM3aIqLs1TIYS\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"},{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"call_a4kxZbiotTZsM3aIqLs1TIYS\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_MAOXFW9Z1yjTHrVUbwrhdgDZ\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\t// Greeting\\n 7|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 8|}\\n</file>\\n\",\"tool_call_id\":\"call_MAOXFW9Z1yjTHrVUbwrhdgDZ\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_Q0CkA8QSKRIzRVl4xl37sxzS\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"description\\\":\\\"Run the Go program to test the output\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Hello, Crush!\\n\\n\\n<cwd>/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool</cwd>\",\"tool_call_id\":\"call_Q0CkA8QSKRIzRVl4xl37sxzS\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

690+ headers:

691+ Accept:

692+ - application/json

693+ Content-Type:

694+ - application/json

695+ User-Agent:

696+ - OpenAI/Go 2.7.1

697+ url: https://api.openai.com/v1/chat/completions

698+ method: POST

699+ response:

700+ proto: HTTP/2.0

701+ proto_major: 2

702+ proto_minor: 0

703+ content_length: -1

704+ body: |+

705+ data: {"id":"chatcmpl-CTnvWWSTS3wNS3gZo5WnCPjP6RyID","object":"chat.completion.chunk","created":1761219466,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"q3GU2fbheu"}

539

706

540− data: {"id":"chatcmpl-CQ4JlEVVZuky9TcnyG7DP5xRewT7E","object":"chat.completion.chunk","created":1760329161,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"mXRroG4Ijgl"}

707+ data: {"id":"chatcmpl-CTnvWWSTS3wNS3gZo5WnCPjP6RyID","object":"chat.completion.chunk","created":1761219466,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"VlycIjXL"}

541

708

542− data: {"id":"chatcmpl-CQ4JlEVVZuky9TcnyG7DP5xRewT7E","object":"chat.completion.chunk","created":1760329161,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"yaEjEY"}

709+ data: {"id":"chatcmpl-CTnvWWSTS3wNS3gZo5WnCPjP6RyID","object":"chat.completion.chunk","created":1761219466,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"t2CrqI"}

543

710

544− data: {"id":"chatcmpl-CQ4JlEVVZuky9TcnyG7DP5xRewT7E","object":"chat.completion.chunk","created":1760329161,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7015,"completion_tokens":5,"total_tokens":7020,"prompt_tokens_details":{"cached_tokens":6912,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Lqete"}

711+ data: {"id":"chatcmpl-CTnvWWSTS3wNS3gZo5WnCPjP6RyID","object":"chat.completion.chunk","created":1761219466,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7030,"completion_tokens":4,"total_tokens":7034,"prompt_tokens_details":{"cached_tokens":6912,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"CsiEW"}

545

712

546 data: [DONE]

713 data: [DONE]

547

714

@@ -550,4 +717,4 @@ interactions:

550 - text/event-stream; charset=utf-8

717 - text/event-stream; charset=utf-8

551 status: 200 OK

718 status: 200 OK

552 code: 200

719 code: 200

553− duration: 1.188596709s

720+ duration: 1.812447166s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/parallel_tool_calls.yaml+94−102

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,25 +24,23 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IBKji8eBlG5W0L"}

27+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"bHMVyt6xB1v0uV"}

29− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Parallel"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OjCAnMWm"}

29+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Parallel"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"jzOxYqvI"}

31− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Execution"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LxVLUu"}

31+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"nZmNYpttsFc"}

33− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" of"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LWv7ie6rzpoDX"}

33+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Search"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1C5S6urQP"}

35− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"XPdu5LcMssX"}

35+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ii9HFHKQ2lNX"}

37− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"n9UqHhUcF4f4"}

37+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Directory"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"iRD6GD"}

39− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" ls"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sMccMq9B4h3E4"}

39+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Listing"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"CDIUZSPI"}

41− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Commands"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"m41DPSw"}

41+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"LsrxflsNPT"}

43− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Iy1hciUjHV"}

43+ data: {"id":"chatcmpl-CToEwK75TXd7qJeIzOE3pfoJSNUui","object":"chat.completion.chunk","created":1761220670,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":154,"completion_tokens":6,"total_tokens":160,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Li6hUjhsWSfr5U"}

44−

45− data: {"id":"chatcmpl-CQ4KMHdk4u1UJ2k9dlt9dRBUBAXUe","object":"chat.completion.chunk","created":1760329198,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":154,"completion_tokens":7,"total_tokens":161,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"10eJs0aPV8q4FH"}

47 data: [DONE]

45 data: [DONE]

@@ -51,22 +49,22 @@ interactions:

51 - text/event-stream; charset=utf-8

49 - text/event-stream; charset=utf-8

52 status: 200 OK

50 status: 200 OK

53 code: 200

51 code: 200

54− duration: 484.404375ms

52+ duration: 1.005567042s

55- id: 1

53- id: 1

56 request:

54 request:

57 proto: HTTP/1.1

55 proto: HTTP/1.1

58 proto_major: 1

56 proto_major: 1

59 proto_minor: 1

57 proto_minor: 1

60− content_length: 30798

58+ content_length: 29954

61 host: ""

59 host: ""

62− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

60+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

63 headers:

61 headers:

64 Accept:

62 Accept:

65 - application/json

63 - application/json

66 Content-Type:

64 Content-Type:

67 - application/json

65 - application/json

68 User-Agent:

66 User-Agent:

69− - OpenAI/Go 2.3.0

67+ - OpenAI/Go 2.7.1

70 url: https://api.openai.com/v1/chat/completions

68 url: https://api.openai.com/v1/chat/completions

71 method: POST

69 method: POST

72 response:

70 response:

@@ -75,55 +73,31 @@ interactions:

75 proto_minor: 0

73 proto_minor: 0

76 content_length: -1

74 content_length: -1

77 body: |+

75 body: |+

78− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null},"finish_reason":null}],"obfuscation":"7w0Vqkp"}

76+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null},"finish_reason":null}],"obfuscation":"bhNo9af"}

79−

80− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_DqMPwc8LX9lsi7tFOaMU0dga","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null}],"obfuscation":"wBQZLfvlER8jU"}

81−

82− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"U0j9qpE11Gkbl"}

83−

84− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ttern"}}]},"finish_reason":null}],"obfuscation":"gz59soEiz7ZXi"}

85−

86− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\": \"**"}}]},"finish_reason":null}],"obfuscation":"OgM6uy6U0B"}

87−

88− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/*.g"}}]},"finish_reason":null}],"obfuscation":"V6JRveSlVcleIe"}

89−

90− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"o\"}"}}]},"finish_reason":null}],"obfuscation":"9KPGGBjttOMFEr"}

91−

92− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"id":"call_X9Qi9x8Ykow99KoJIhO7NZtk","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null}],"obfuscation":"JVsSrJ38JGQSkzl"}

93−

94− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"ZgRNbZPVqGK7J"}

95−

96− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"th\": "}}]},"finish_reason":null}],"obfuscation":"W1scjhNulECw"}

97−

98− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"\"/tmp/"}}]},"finish_reason":null}],"obfuscation":"faQTfLMNzkq"}

100− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"crus"}}]},"finish_reason":null}],"obfuscation":"SwntqyZCvQ4BMe"}

78+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_t9ds8paXUgezedpaEr7HxPPX","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null}],"obfuscation":"pS66wwZcPHIQe"}

101

102− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"h-tes"}}]},"finish_reason":null}],"obfuscation":"IUU3NTPFnKRc9"}

80+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"LuScCaSrWkAj5"}

103

104− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"t/Test"}}]},"finish_reason":null}],"obfuscation":"UHAH0GAmIQ8Z"}

82+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ttern"}}]},"finish_reason":null}],"obfuscation":"Faze21uRmM8hk"}

105

106− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"Code"}}]},"finish_reason":null}],"obfuscation":"j0p8NGCISH61rp"}

84+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\": \"**"}}]},"finish_reason":null}],"obfuscation":"fud14v8vkS"}

107

108− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"rAgen"}}]},"finish_reason":null}],"obfuscation":"IZj0iKAh1w1Iq"}

86+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/*.g"}}]},"finish_reason":null}],"obfuscation":"zIcLvobaNobmgI"}

109

110− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"t/open"}}]},"finish_reason":null}],"obfuscation":"77rUL0QGxSyb"}

88+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"o\"}"}}]},"finish_reason":null}],"obfuscation":"fCx4jGyllZupnt"}

111

112− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"ai-g"}}]},"finish_reason":null}],"obfuscation":"mUit8qIPAMcDW3"}

90+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"id":"call_ZkWUeH8iZguAbGcFxLK2zKN9","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null}],"obfuscation":"whp5aWubeKoMIj0"}

113

114− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"pt-5/"}}]},"finish_reason":null}],"obfuscation":"gG0WRyQnk9Hwi"}

92+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"bq2nj0xBHNlRh"}

115

116− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"parall"}}]},"finish_reason":null}],"obfuscation":"0oaq2lc9EfFF"}

94+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"th\": "}}]},"finish_reason":null}],"obfuscation":"oC0PTIBaRffU"}

117

118− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"el_t"}}]},"finish_reason":null}],"obfuscation":"EgVoeVNGGH0fGV"}

96+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"\".\"}"}}]},"finish_reason":null}],"obfuscation":"WVu5VV9lkXmN"}

119

120− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"ool_c"}}]},"finish_reason":null}],"obfuscation":"hukLAVxSNuRlJ"}

98+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

121

122− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"alls\"}"}}]},"finish_reason":null}],"obfuscation":"VUUpnYm1DWE"}

100+ data: {"id":"chatcmpl-CToEwNewROMaaTkMHjbJIKHWe2pFO","object":"chat.completion.chunk","created":1761220670,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6492,"completion_tokens":374,"total_tokens":6866,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"kQMJ"}

123−

124− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

125−

126− data: {"id":"chatcmpl-CQ4KMdFAK6KgIGEaXnBQVMbEgZscU","object":"chat.completion.chunk","created":1760329198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6591,"completion_tokens":327,"total_tokens":6918,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"g"}

127

101

128 data: [DONE]

102 data: [DONE]

129

103

@@ -132,22 +106,22 @@ interactions:

132 - text/event-stream; charset=utf-8

106 - text/event-stream; charset=utf-8

133 status: 200 OK

107 status: 200 OK

134 code: 200

108 code: 200

135− duration: 9.554137917s

109+ duration: 12.659725167s

136- id: 2

110- id: 2

137 request:

111 request:

138 proto: HTTP/1.1

112 proto: HTTP/1.1

139 proto_major: 1

113 proto_major: 1

140 proto_minor: 1

114 proto_minor: 1

141− content_length: 31453

115+ content_length: 30547

142 host: ""

116 host: ""

143− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_DqMPwc8LX9lsi7tFOaMU0dga\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_X9Qi9x8Ykow99KoJIhO7NZtk\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_DqMPwc8LX9lsi7tFOaMU0dga\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_X9Qi9x8Ykow99KoJIhO7NZtk\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

117+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_t9ds8paXUgezedpaEr7HxPPX\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_ZkWUeH8iZguAbGcFxLK2zKN9\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_t9ds8paXUgezedpaEr7HxPPX\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_ZkWUeH8iZguAbGcFxLK2zKN9\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

144 headers:

118 headers:

145 Accept:

119 Accept:

146 - application/json

120 - application/json

147 Content-Type:

121 Content-Type:

148 - application/json

122 - application/json

149 User-Agent:

123 User-Agent:

150− - OpenAI/Go 2.3.0

124+ - OpenAI/Go 2.7.1

151 url: https://api.openai.com/v1/chat/completions

125 url: https://api.openai.com/v1/chat/completions

152 method: POST

126 method: POST

153 response:

127 response:

@@ -156,93 +130,111 @@ interactions:

156 proto_minor: 0

130 proto_minor: 0

157 content_length: -1

131 content_length: -1

158 body: |+

132 body: |+

159− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"yvwetVWACr"}

133+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"PdQnf2LmTv"}

134+

135+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"0FPMKLstlX4"}

136+

137+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"5JwoC51Ob"}

138+

139+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"QGHEiY8lT"}

140+

141+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"k2n92hXD5"}

142+

143+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"4GsUjgr"}

144+

145+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"sTlhVxh"}

146+

147+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"3YHosW2"}

148+

149+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"LbJUGjQ"}

150+

151+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"1sZJV7T"}

160

152

161− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"eTAMEozafg7"}

153+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"wCnLHonGsP"}

162

154

163− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" ."},"finish_reason":null}],"usage":null,"obfuscation":"OniQsIUshU"}

155+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"b5PPC768su"}

164

156

165− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"Elet3P0UWR"}

157+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"MDSPzfW64u"}

166

158

167− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}],"usage":null,"obfuscation":"KjV8z8"}

159+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"Fs4tmxTUOCm"}

168

160

169− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":\n"},"finish_reason":null}],"usage":null,"obfuscation":"afOjKsNi6"}

161+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"yUzmapwmkKr"}

170

162

171− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"4gIOR0ESO2h"}

163+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"5RL6yWPufUo"}

172

164

173− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"Oi9E6xBFHA"}

165+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"parallel"},"finish_reason":null}],"usage":null,"obfuscation":"VSEo"}

174

166

175− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" /"},"finish_reason":null}],"usage":null,"obfuscation":"Fqsylc0b2o"}

167+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"5QRzkm5"}

176

168

177− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"UjXGejbNr"}

169+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_calls"},"finish_reason":null}],"usage":null,"obfuscation":"TRHZvF"}

178

170

179− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"tLWtdSOby"}

171+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"TKOLR01"}

180

172

181− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"JjjQKCXaA"}

173+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"0y185oWwM"}

182

174

183− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"fvbye78"}

175+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n\n"},"finish_reason":null}],"usage":null,"obfuscation":"SEBZjh4h"}

184

176

185− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"N2sbuQQ"}

177+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"7oYbkBbcMng"}

186

178

187− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"Yy3ZaIA"}

179+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" /"},"finish_reason":null}],"usage":null,"obfuscation":"VunnogPswd"}

188

180

189− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"CzIIzds"}

181+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"H1fRWyY5p"}

190

182

191− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"MVuT2mI"}

183+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"4lu7fC87w"}

192

184

193− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"KzHqJOFpUR"}

185+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"c7kOPw1Hl"}

194

186

195− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"aoJBwwTi4c"}

187+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"cbd2MIZ"}

196

188

197− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"tClP1ey8Ww"}

189+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"OUux6av"}

198

190

199− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"gG943apt0aB"}

191+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"TrzXT95"}

200

192

201− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"SuPPxkArMdc"}

193+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"yTemqf4"}

202

194

203− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"t6VXyyMSeqT"}

195+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"E1SPeoq"}

204

196

205− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"parallel"},"finish_reason":null}],"usage":null,"obfuscation":"2M5k"}

197+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"CoX4NIfVgX"}

206

198

207− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"S7Mp22U"}

199+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"vPo2fMMRd6"}

208

200

209− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_calls"},"finish_reason":null}],"usage":null,"obfuscation":"b4ltWZ"}

201+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"kLByTFIX6z"}

210

202

211− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"vfRz2bH"}

203+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"vYr4uGTLxRd"}

212

204

213− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"cx4UbwSRP"}

205+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"WWjUF9yd2TY"}

214

206

215− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"2BPHgNHUBp"}

207+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"PDzrqFb6tHF"}

216

208

217− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"1Xzwjiq7Vav"}

209+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"parallel"},"finish_reason":null}],"usage":null,"obfuscation":"GiRK"}

218

210

219− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" Current"},"finish_reason":null}],"usage":null,"obfuscation":"lxIC"}

211+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"1kD9XEs"}

220

212

221− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" directory"},"finish_reason":null}],"usage":null,"obfuscation":"fQ"}

213+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_calls"},"finish_reason":null}],"usage":null,"obfuscation":"hI29CB"}

222

214

223− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":\n"},"finish_reason":null}],"usage":null,"obfuscation":"nwOgsAwPh"}

215+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/\n"},"finish_reason":null}],"usage":null,"obfuscation":"Pcod0FPRo"}

224

216

225− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"DmjqbBYaxBl"}

217+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"C5UbeTP4l4I"}

226

218

227− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"2hEeyKW3Jj"}

219+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"NOu7fyq6dY"}

228

220

229− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" go"},"finish_reason":null}],"usage":null,"obfuscation":"MkAAKowgX"}

221+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" go"},"finish_reason":null}],"usage":null,"obfuscation":"7fyY9ug63"}

230

222

231− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"7Djt2ayv"}

223+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"IBzvNXO3"}

232

224

233− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"EPes3Z7nGF"}

225+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"NrBFIqJc6T"}

234

226

235− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"8oCKV6LqKzz"}

227+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"2Djt662GOgr"}

236

228

237− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"MOTd73VV6G"}

229+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"bbnG6DTvES"}

238

230

239− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"CBLIU3Y"}

231+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"gFMAbpi"}

240

232

241− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"DCXuTDVgt"}

233+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"t4BQcnngN"}

242

234

243− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"C3wHR7"}

235+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"39Vzf5"}

244

236

245− data: {"id":"chatcmpl-CQ4KWZn1KXStFdQnela7SuBqidXc6","object":"chat.completion.chunk","created":1760329208,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6725,"completion_tokens":44,"total_tokens":6769,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"b9ZV"}

237+ data: {"id":"chatcmpl-CToF9vmDCqMRm1InQZSrHmRm0jOSA","object":"chat.completion.chunk","created":1761220683,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6609,"completion_tokens":53,"total_tokens":6662,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Ubh9"}

246

238

247 data: [DONE]

239 data: [DONE]

248

240

@@ -251,4 +243,4 @@ interactions:

251 - text/event-stream; charset=utf-8

243 - text/event-stream; charset=utf-8

252 status: 200 OK

244 status: 200 OK

253 code: 200

245 code: 200

254− duration: 1.377417792s

246+ duration: 1.429721541s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/read_a_file.yaml+102−102

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,19 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"3L5ZUjxDTQefz3"}

27+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OZGOOTOnArqkyY"}

29− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"35TlzXA01rHVQt"}

29+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Read"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"T5palGdgdukY"}

31− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Mod"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"bratQdQU9oOM"}

31+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" the"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"RpI9b6mPMRzc"}

33− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Read"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9YtAhDpKXUO"}

33+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8BGtjXOZSm1nL"}

35− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Instruction"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"uvbe"}

35+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Mod"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HHO6uHLIbBfb"}

37− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Q3I6sjrptX"}

37+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"3prpOfF449"}

39− data: {"id":"chatcmpl-CQ4HNEOUviqowtv5WmMEkM9QNXa7D","object":"chat.completion.chunk","created":1760329013,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":129,"completion_tokens":4,"total_tokens":133,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"8Czkjx94tA13YY"}

39+ data: {"id":"chatcmpl-CTnsSU03iSgMmulBkJwLpFHe8XHpa","object":"chat.completion.chunk","created":1761219276,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":129,"completion_tokens":4,"total_tokens":133,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"8CaRnllHN48CLN"}

41 data: [DONE]

@@ -45,22 +45,22 @@ interactions:

45 - text/event-stream; charset=utf-8

46 status: 200 OK

47 code: 200

48− duration: 1.368187875s

48+ duration: 509.348833ms

49- id: 1

50 request:

51 proto: HTTP/1.1

52 proto_major: 1

53 proto_minor: 1

54− content_length: 30671

54+ content_length: 29827

55 host: ""

56− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

57 headers:

58 Accept:

59 - application/json

60 Content-Type:

61 - application/json

62 User-Agent:

63− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

64 url: https://api.openai.com/v1/chat/completions

65 method: POST

66 response:

@@ -69,67 +69,65 @@ interactions:

69 proto_minor: 0

70 content_length: -1

71 body: |+

72− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_L4TfTCIQFlGeHXi2rBtT1wjf","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"nVIG6VSSQ8d5"}

72+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_KxFioKxAz63IlSbNL9iWRYh5","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"iqfdQHIlF2ioXd"}

74− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"M8d463qcJYlOtX2"}

74+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"OHK6Rjqg3IcSmif"}

76− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ct6P8glAFMs"}

76+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vW9JrRjYfmG2k0"}

78− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ofzAQmvhSFcGw"}

78+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n6gDY8fH40nbytr"}

80− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"**"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

80+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fXiCv7Gm0m7DEa"}

82− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c"}

82+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EbRpZWBA8IwfrDm"}

84− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

84+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DE1cmnx6r9Jht1B"}

86− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4kn0nX51ufDQiL"}

86+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ddU8aA9eVFBWfXH"}

88− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"7p2najfhIQ1VT"}

88+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2zqPsUINWIFa2"}

90− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OYUOmMxyfcG9PX"}

90+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AXMHqlD6pa1do"}

92− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZBOdTGl4fmR2Bot"}

92+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KbkSjF2kxTokF"}

94− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VDoHE3UdPDbFzeD"}

94+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Jn9UgGBFHa9EJ"}

96− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HTpA6TxcGzTQzid"}

96+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MG1eL3OPJK6cP"}

98− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qdfeEq3pmIqLDsC"}

98+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

100− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7GMRPyP5cuRyVF9"}

100+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

101

102− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"v6xuLWnUOGFLk"}

102+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

103

104− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RYdqFpenCqLbW"}

104+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s"}

105

106− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0XjaVI5EL8BmU"}

106+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y"}

107

108− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gLaUwm269rFgS"}

108+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jkOLw7u4LJOzF"}

109

110− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bRVBBMWaGUXxs"}

110+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

111

112− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

112+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1h8cyvHGLSDmg"}

113

114− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

114+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z0ZTxzTSu5AKO1y"}

115

116− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

116+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"i8fmVDJkwIu4DyO"}

117

118− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}

118+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"u6wPlZtaLmuTi"}

119

120− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B"}

120+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l85zVANMcd3fbzd"}

121

122− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wo2uARcHknOkx"}

122+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"}

123

124− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

124+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"}

125

126− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y1MlcPwhFHuiz"}

126+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3"}

127

128− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SHqjBymNPlEFVde"}

128+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

129

130− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

130+ data: {"id":"chatcmpl-CTnsTlJdHtKSFwrXwjs8jSHdWJ1ji","object":"chat.completion.chunk","created":1761219277,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6466,"completion_tokens":557,"total_tokens":7023,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":512,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"P"}

131−

132− data: {"id":"chatcmpl-CQ4HNEQDleUAEFXT70R0kon99vjZv","object":"chat.completion.chunk","created":1760329013,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6565,"completion_tokens":365,"total_tokens":6930,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Z"}

133

131

134 data: [DONE]

132 data: [DONE]

135

133

@@ -138,22 +136,22 @@ interactions:

138 - text/event-stream; charset=utf-8

136 - text/event-stream; charset=utf-8

139 status: 200 OK

137 status: 200 OK

140 code: 200

138 code: 200

141− duration: 10.521129416s

139+ duration: 10.472917584s

142- id: 2

140- id: 2

143 request:

141 request:

144 proto: HTTP/1.1

142 proto: HTTP/1.1

145 proto_major: 1

143 proto_major: 1

146 proto_minor: 1

144 proto_minor: 1

147− content_length: 31040

145+ content_length: 30208

148 host: ""

146 host: ""

149− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_L4TfTCIQFlGeHXi2rBtT1wjf\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/go.mod\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\",\"tool_call_id\":\"call_L4TfTCIQFlGeHXi2rBtT1wjf\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

147+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_KxFioKxAz63IlSbNL9iWRYh5\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_KxFioKxAz63IlSbNL9iWRYh5\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

150 headers:

148 headers:

151 Accept:

149 Accept:

152 - application/json

150 - application/json

153 Content-Type:

151 Content-Type:

154 - application/json

152 - application/json

155 User-Agent:

153 User-Agent:

156− - OpenAI/Go 2.3.0

154+ - OpenAI/Go 2.7.1

157 url: https://api.openai.com/v1/chat/completions

155 url: https://api.openai.com/v1/chat/completions

158 method: POST

156 method: POST

159 response:

157 response:

@@ -162,59 +160,69 @@ interactions:

162 proto_minor: 0

160 proto_minor: 0

163 content_length: -1

161 content_length: -1

164 body: |+

162 body: |+

165− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_5P3z7Fe7q8HNwWM3jhx7UQDL","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"mwPkLnH5YuYh"}

163+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_BEKV0KwPKJh5IvMLOJZrIGtZ","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"mMUidbQfhs0I"}

164+

165+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"TiEHeQSszEB6rcU"}

166+

167+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Avl38KHfKc3cQc"}

168+

169+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vyM9al6iK5MSe"}

170+

171+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZgWRINtxEARXyFB"}

166

172

167− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qwyyv0lDKsUAyXm"}

173+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GZ0ejyAN0kq8KCx"}

168

174

169− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"i6giRT254v3aNB"}

175+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WGjWRZQOnvCpoBh"}

170

176

171− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"O6EzcojF5FPoH"}

177+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AISMw6fPkNNiFKS"}

172

178

173− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oo2ScAcqzeZNU5O"}

179+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zK2oR7MzEl5GSCv"}

174

180

175− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JfQTrUZ3MKaJj2W"}

181+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0x3BJMyJIVFZa"}

176

182

177− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DhicEOOsXzI1eIH"}

183+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YBM9bfXaJ9AFo"}

178

184

179− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vMGkq0MkgzjFoLv"}

185+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YAHeuIUU1C25I"}

180

186

181− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C7mleNmhCHaex4s"}

187+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xgc4769psA6Ez"}

182

188

183− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m36d8HEC438yM"}

189+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ADAW9qAO2mpIg"}

184

190

185− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yI8KiVTfoHYl8"}

191+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

186

192

187− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IeYSi6j4ID06A"}

193+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

188

194

189− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TIOvLBR4ECRqn"}

195+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

190

196

191− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T75ghUZHhozcZ"}

197+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d"}

192

198

193− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

199+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"}

194

200

195− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

201+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dfz7RsJrh5vSJ"}

196

202

197− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

203+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

198

204

199− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"}

205+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4PV2CveVnndE6"}

200

206

201− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A"}

207+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0zrZHkv8DPe93ZS"}

202

208

203− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r2b7T8Y9lLi8g"}

209+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0H4edvmgxhESEa"}

204

210

205− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

211+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"3oarIZq2zitDg"}

206

212

207− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FSzzjWNveoZYi"}

213+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"limit"}}]},"finish_reason":null}],"usage":null,"obfuscation":"36E0fd53Y4ZXH"}

208

214

209− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X8spJfkJFfZGC35"}

215+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MniTHGf6F68VYDw"}

210

216

211− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"E6x78LnoOvsWq0"}

217+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"200"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7vtXvaRPK6LY3xk"}

212

218

213− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UzTwLzt3P8wbh8v"}

219+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"a"}

214

220

215− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

221+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"k"}

216

222

217− data: {"id":"chatcmpl-CQ4HYSTnkzrWylpTuCAEUK5L0xabr","object":"chat.completion.chunk","created":1760329024,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6632,"completion_tokens":35,"total_tokens":6667,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"kWHd"}

223+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

224+

225+ data: {"id":"chatcmpl-CTnseJzEIuX6pjRMfTe1KglN72O6r","object":"chat.completion.chunk","created":1761219288,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6543,"completion_tokens":110,"total_tokens":6653,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"5Adiy"}

218

226

219 data: [DONE]

227 data: [DONE]

220

228

@@ -223,22 +231,22 @@ interactions:

223 - text/event-stream; charset=utf-8

231 - text/event-stream; charset=utf-8

224 status: 200 OK

232 status: 200 OK

225 code: 200

233 code: 200

226− duration: 1.96976775s

234+ duration: 5.66224525s

227- id: 3

235- id: 3

228 request:

236 request:

229 proto: HTTP/1.1

237 proto: HTTP/1.1

230 proto_major: 1

238 proto_major: 1

231 proto_minor: 1

239 proto_minor: 1

232− content_length: 31414

240+ content_length: 30597

233 host: ""

241 host: ""

234− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_L4TfTCIQFlGeHXi2rBtT1wjf\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/go.mod\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\",\"tool_call_id\":\"call_L4TfTCIQFlGeHXi2rBtT1wjf\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_5P3z7Fe7q8HNwWM3jhx7UQDL\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_5P3z7Fe7q8HNwWM3jhx7UQDL\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

242+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_KxFioKxAz63IlSbNL9iWRYh5\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_KxFioKxAz63IlSbNL9iWRYh5\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_BEKV0KwPKJh5IvMLOJZrIGtZ\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\\\",\\\"limit\\\":2000}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_BEKV0KwPKJh5IvMLOJZrIGtZ\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

235 headers:

243 headers:

236 Accept:

244 Accept:

237 - application/json

245 - application/json

238 Content-Type:

246 Content-Type:

239 - application/json

247 - application/json

240 User-Agent:

248 User-Agent:

241− - OpenAI/Go 2.3.0

249+ - OpenAI/Go 2.7.1

242 url: https://api.openai.com/v1/chat/completions

250 url: https://api.openai.com/v1/chat/completions

243 method: POST

251 method: POST

244 response:

252 response:

@@ -247,41 +255,33 @@ interactions:

247 proto_minor: 0

255 proto_minor: 0

248 content_length: -1

256 content_length: -1

249 body: |+

257 body: |+

250− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"I4kQetoUuQ"}

258+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"j4dbE0kTCk"}

251−

252− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"``"},"finish_reason":null}],"usage":null,"obfuscation":"FPEEfbJxgG"}

253−

254− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"`\n"},"finish_reason":null}],"usage":null,"obfuscation":"oWRknhgW6"}

255−

256− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"module"},"finish_reason":null}],"usage":null,"obfuscation":"HA7opJ"}

257−

258− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}],"usage":null,"obfuscation":"VB0G"}

259

260− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"zbRfAoIl"}

260+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"module"},"finish_reason":null}],"usage":null,"obfuscation":"6Q0LrV"}

261

262− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/test"},"finish_reason":null}],"usage":null,"obfuscation":"Uhk7pH8"}

262+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}],"usage":null,"obfuscation":"XyzL"}

263

264− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"project"},"finish_reason":null}],"usage":null,"obfuscation":"JQ6LV"}

264+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"Y6GK6xuY"}

265

266− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n\n"},"finish_reason":null}],"usage":null,"obfuscation":"0RZKDanv"}

266+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/test"},"finish_reason":null}],"usage":null,"obfuscation":"N4jTfo1"}

267

268− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"zsYANIs4pO"}

268+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"project"},"finish_reason":null}],"usage":null,"obfuscation":"kTH4N"}

269

270− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"cnr3hy3FL8N"}

270+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n\n"},"finish_reason":null}],"usage":null,"obfuscation":"Jqps5cPs"}

271

272− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"l4iHyva5fku"}

272+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"Yf1vSs2898"}

273

274− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"zRlDZ003oTb"}

274+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"QXt5BLFzSAp"}

275

276− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"23"},"finish_reason":null}],"usage":null,"obfuscation":"b4wvxXf51C"}

276+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"8OGx6Z4w8v1"}

277

278− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"cxhOPlsmEm"}

278+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"ZDeV3KAhdMY"}

279

280− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"```"},"finish_reason":null}],"usage":null,"obfuscation":"CvXL7lHT2"}

280+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"23"},"finish_reason":null}],"usage":null,"obfuscation":"RwHjNbyxQz"}

281

282− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"o9OiK7"}

282+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"FVOxF5"}

283

284− data: {"id":"chatcmpl-CQ4HZWAMDuRFTZgVEEDyfzfxLoxCW","object":"chat.completion.chunk","created":1760329025,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6707,"completion_tokens":280,"total_tokens":6987,"prompt_tokens_details":{"cached_tokens":6656,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"L"}

284+ data: {"id":"chatcmpl-CTnsjiK956U3yJcNNGnNY9TV135ba","object":"chat.completion.chunk","created":1761219293,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6623,"completion_tokens":14,"total_tokens":6637,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"NjZJ"}

285

286 data: [DONE]

287

@@ -290,4 +290,4 @@ interactions:

290 - text/event-stream; charset=utf-8

291 status: 200 OK

292 code: 200

293− duration: 5.711255125s

293+ duration: 1.844991375s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/simple_test.yaml+17−15

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,15 +24,17 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4HJDRXTRBbIWdJgGxI2eN7HgLMo","object":"chat.completion.chunk","created":1760329009,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"xFGewoulgnen9l"}

27+ data: {"id":"chatcmpl-CTnsPHq388hN9VuFmjDpHiUPlxa84","object":"chat.completion.chunk","created":1761219273,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"97Cy9xN03PqdzK"}

29− data: {"id":"chatcmpl-CQ4HJDRXTRBbIWdJgGxI2eN7HgLMo","object":"chat.completion.chunk","created":1760329009,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":"Greeting"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VEgWrw6a"}

29+ data: {"id":"chatcmpl-CTnsPHq388hN9VuFmjDpHiUPlxa84","object":"chat.completion.chunk","created":1761219273,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Greetings"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"CpDjM66"}

31− data: {"id":"chatcmpl-CQ4HJDRXTRBbIWdJgGxI2eN7HgLMo","object":"chat.completion.chunk","created":1760329009,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{"content":" Message"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"PeHw29gC"}

31+ data: {"id":"chatcmpl-CTnsPHq388hN9VuFmjDpHiUPlxa84","object":"chat.completion.chunk","created":1761219273,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"UxTRIMjPP4Qt"}

33− data: {"id":"chatcmpl-CQ4HJDRXTRBbIWdJgGxI2eN7HgLMo","object":"chat.completion.chunk","created":1760329009,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"ydBOd29BPU"}

33+ data: {"id":"chatcmpl-CTnsPHq388hN9VuFmjDpHiUPlxa84","object":"chat.completion.chunk","created":1761219273,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Introduction"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"kEr"}

35− data: {"id":"chatcmpl-CQ4HJDRXTRBbIWdJgGxI2eN7HgLMo","object":"chat.completion.chunk","created":1760329009,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_f64f290af2","choices":[],"usage":{"prompt_tokens":126,"completion_tokens":2,"total_tokens":128,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"w3oWFN1yHa2XIn"}

35+ data: {"id":"chatcmpl-CTnsPHq388hN9VuFmjDpHiUPlxa84","object":"chat.completion.chunk","created":1761219273,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"VzGq8TKPi7"}

36+

37+ data: {"id":"chatcmpl-CTnsPHq388hN9VuFmjDpHiUPlxa84","object":"chat.completion.chunk","created":1761219273,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":126,"completion_tokens":3,"total_tokens":129,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"I36B3yNq4eVBsW"}

37 data: [DONE]

39 data: [DONE]

@@ -41,22 +43,22 @@ interactions:

41 - text/event-stream; charset=utf-8

43 - text/event-stream; charset=utf-8

42 status: 200 OK

44 status: 200 OK

43 code: 200

45 code: 200

44− duration: 1.519493875s

46+ duration: 1.084419333s

45- id: 1

47- id: 1

46 request:

48 request:

47 proto: HTTP/1.1

49 proto: HTTP/1.1

48 proto_major: 1

50 proto_major: 1

49 proto_minor: 1

51 proto_minor: 1

50− content_length: 30661

52+ content_length: 29817

51 host: ""

53 host: ""

52− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/simple_test\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

54+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

53 headers:

55 headers:

54 Accept:

56 Accept:

55 - application/json

57 - application/json

56 Content-Type:

58 Content-Type:

57 - application/json

59 - application/json

58 User-Agent:

60 User-Agent:

59− - OpenAI/Go 2.3.0

61+ - OpenAI/Go 2.7.1

60 url: https://api.openai.com/v1/chat/completions

62 url: https://api.openai.com/v1/chat/completions

61 method: POST

63 method: POST

62 response:

64 response:

@@ -65,13 +67,13 @@ interactions:

65 proto_minor: 0

67 proto_minor: 0

66 content_length: -1

68 content_length: -1

67 body: |+

69 body: |+

68− data: {"id":"chatcmpl-CQ4HJBxYtLwds4DG284uO8SQ2tumR","object":"chat.completion.chunk","created":1760329009,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"VNMEKpx1OU"}

70+ data: {"id":"chatcmpl-CTnsQ2kXJ4tEMo8SjWlQJH0NZ4hHV","object":"chat.completion.chunk","created":1761219274,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"6wPJk1PqzC"}

70− data: {"id":"chatcmpl-CQ4HJBxYtLwds4DG284uO8SQ2tumR","object":"chat.completion.chunk","created":1760329009,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}],"usage":null,"obfuscation":"w64PjcnAVR"}

72+ data: {"id":"chatcmpl-CTnsQ2kXJ4tEMo8SjWlQJH0NZ4hHV","object":"chat.completion.chunk","created":1761219274,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}],"usage":null,"obfuscation":"LsVhgfCRbM"}

72− data: {"id":"chatcmpl-CQ4HJBxYtLwds4DG284uO8SQ2tumR","object":"chat.completion.chunk","created":1760329009,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"tSFp7C"}

74+ data: {"id":"chatcmpl-CTnsQ2kXJ4tEMo8SjWlQJH0NZ4hHV","object":"chat.completion.chunk","created":1761219274,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"kPve2p"}

74− data: {"id":"chatcmpl-CQ4HJBxYtLwds4DG284uO8SQ2tumR","object":"chat.completion.chunk","created":1760329009,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6561,"completion_tokens":74,"total_tokens":6635,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"WYylgo"}

76+ data: {"id":"chatcmpl-CTnsQ2kXJ4tEMo8SjWlQJH0NZ4hHV","object":"chat.completion.chunk","created":1761219274,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6462,"completion_tokens":74,"total_tokens":6536,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ZPj"}

76 data: [DONE]

78 data: [DONE]

@@ -80,4 +82,4 @@ interactions:

80 - text/event-stream; charset=utf-8

82 - text/event-stream; charset=utf-8

81 status: 200 OK

83 status: 200 OK

82 code: 200

84 code: 200

83− duration: 4.197205334s

85+ duration: 3.64046325s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/sourcegraph_tool.yaml+181−180

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,35 +24,35 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"iJwvMpfZfzB5bk"}

27+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rDSzI9962EPhz9"}

29− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Searching"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"y7o1uQY"}

29+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Searching"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8tdQ1t0"}

31− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"PM47cMBcjGLEKT"}

31+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"hj0taOjFubCa3H"}

33− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"func"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"6EtlYyuGmMld"}

33+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"func"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"keBYzaBOssVk"}

35− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"514JAqsNKLH"}

35+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"cttyPqxVuh4"}

37− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"JBBPg9XoQi39VxM"}

37+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"JBnCCjbV0Q30iPH"}

39− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"TMQwPsCtUcNYZ"}

39+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OCqKWjsaqS47X"}

41− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0Xl3vRumPnbIS"}

41+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"CBQwU4UQhQ1r9"}

43− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Re"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LXqj6NsXBQ7Go"}

43+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Re"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ItEEr5WdGnwwk"}

45− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"positories"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"tTGpW2"}

45+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"positories"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"3KpHpo"}

47− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"fgCaBPcP4PZ"}

47+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"daSs4KZZEk0"}

49− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Source"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ydVcdMZBn"}

49+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Source"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ePojNKSFv"}

51− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"graph"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"EG14PUcnoi1"}

51+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"graph"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QQXCeVjuufP"}

53− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"AMYUYsnGYO"}

53+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"cnCxwT4ebg"}

55− data: {"id":"chatcmpl-CQ4JmoqU1CR5huBIh7RplQ9VlfzoZ","object":"chat.completion.chunk","created":1760329162,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":12,"total_tokens":150,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"xwYf2fZNUoxZo"}

55+ data: {"id":"chatcmpl-CTnvX6OF7gHcRK2h6A9EJhAVsmIkF","object":"chat.completion.chunk","created":1761219467,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":12,"total_tokens":150,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"cCkh0KGoATByQ"}

57 data: [DONE]

@@ -61,22 +61,22 @@ interactions:

61 - text/event-stream; charset=utf-8

62 status: 200 OK

63 code: 200

64− duration: 435.95325ms

64+ duration: 501.56625ms

65- id: 1

66 request:

67 proto: HTTP/1.1

68 proto_major: 1

69 proto_minor: 1

70− content_length: 30721

70+ content_length: 29877

71 host: ""

72− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

72+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

73 headers:

74 Accept:

75 - application/json

76 Content-Type:

77 - application/json

78 User-Agent:

79− - OpenAI/Go 2.3.0

79+ - OpenAI/Go 2.7.1

80 url: https://api.openai.com/v1/chat/completions

81 method: POST

82 response:

@@ -85,47 +85,61 @@ interactions:

85 proto_minor: 0

86 content_length: -1

87 body: |+

88− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_AJDsEhKmOO55HF5w0B78Wl2C","type":"function","function":{"name":"sourcegraph","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"LoNWs"}

88+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_eG1GRwBeCLOUWghVcDdwhumF","type":"function","function":{"name":"sourcegraph","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"KNwnd"}

90− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"o6Z2ClEpgTRrgzR"}

90+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"B4F34BsTzo9ImPq"}

92− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"query"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y69YlKVoeyAtj"}

92+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"query"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FV2Suqb4wCJ5C"}

94− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"DbrdNRBfTh0Ev"}

94+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"BDqk9igcRqCLa"}

96− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lang"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Om5XEbaGmcxPhi"}

96+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lang"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P717JzJq2LNTGf"}

98− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"}

98+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"J"}

100− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

100+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

101

102− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"C22leLYGqBwem"}

102+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wIw4eebMDZ"}

103

104− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ihUr8fY7cjOz6p"}

104+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"TpBdz0RijeNlT"}

105

106− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zWejQPa9pSZXr"}

106+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"29EFXQdjTDGKvA"}

107

108− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"yBLcSjjCWGyasU"}

108+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T8yBXZv7fHNb0"}

109

110− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" type"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WE0Cl17y9zsHI"}

110+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"FgLNODazvhmtM"}

111

112− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HhWROdAnbBk1I"}

112+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" type"}}]},"finish_reason":null}],"usage":null,"obfuscation":"h8xgJhaM1LlF8"}

113

114− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" select"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d3gbsmm1vz2"}

114+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QA3jh0efyPZpz"}

115

116− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IXS53iv8cUx8H"}

116+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aYeMDjHeYfTY"}

117

118− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4z4vB6n31KYE"}

118+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"}

119

120− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"}

120+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

121

122− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

122+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"IGodqFItJQ40l"}

123

124− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l3wcEiUDc683ae0"}

124+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Og2lcFbwqnX3i"}

125

126− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

126+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"noTpYKhwwWqhc2c"}

127

128− data: {"id":"chatcmpl-CQ4Jm2ZvOcv6ht8YcdPzMAB7ZhS5b","object":"chat.completion.chunk","created":1760329162,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6574,"completion_tokens":484,"total_tokens":7058,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":448,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"b"}

128+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

129+

130+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"h53MYNr1CbGqYil"}

131+

132+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"a9HbkwMF16b"}

133+

134+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V5voHkwgyW8MVOa"}

135+

136+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

137+

138+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7"}

139+

140+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

141+

142+ data: {"id":"chatcmpl-CTnvXZsU9yAibW6raxyo30ActhbA0","object":"chat.completion.chunk","created":1761219467,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6475,"completion_tokens":299,"total_tokens":6774,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"GBDU"}

129

143

130 data: [DONE]

144 data: [DONE]

131

145

@@ -134,15 +148,15 @@ interactions:

134 - text/event-stream; charset=utf-8

148 - text/event-stream; charset=utf-8

135 status: 200 OK

149 status: 200 OK

136 code: 200

150 code: 200

137− duration: 12.618703791s

151+ duration: 9.563071792s

138- id: 2

152- id: 2

139 request:

153 request:

140 proto: HTTP/1.1

154 proto: HTTP/1.1

141 proto_major: 1

155 proto_major: 1

142 proto_minor: 1

156 proto_minor: 1

143− content_length: 459

157+ content_length: 456

144 host: sourcegraph.com

158 host: sourcegraph.com

145− body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go \"func main\" type:file select:file count:10"}}'

159+ body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go content:\"func main(\" type:file count:10"}}'

146 headers:

160 headers:

147 Content-Type:

161 Content-Type:

148 - application/json

162 - application/json

@@ -156,28 +170,28 @@ interactions:

156 proto_minor: 0

170 proto_minor: 0

157 content_length: -1

171 content_length: -1

158 uncompressed: true

172 uncompressed: true

159− body: '{"data":{"search":{"results":{"matchCount":10,"limitHit":true,"resultCount":10,"approximateResultCount":"10+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"translation/chinese/02-编写第一个程序/main.go","url":"/github.com/inancgumus/learngo/-/blob/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main 是一个特殊的包\n// 它允许 Go 创建一个可执行文件\npackage main\n\n/*\n这是一个多行注释\n\nimport 关键字引入另一个包\n 对于这个 .go ”文件“\n\nimport \"fmt\" 允许你使用 fmt 包的各种函数\n 在这个文件\n*/\nimport \"fmt\"\n\n// \"func main\" 是特殊的\n//\n// Go 必须知道从哪里开始执行\n//\n// func main 对于 Go 而言就是开始执行的位置\n//\n// 代码编译后，\n// Go runtime 第一个执行该函数\nfunc main() {\n\t// import \"fmt\" 之后\n\t// \"fmt\" 包中的 Println 函数就可以使用\n\n\t// 在控制台输入下面的命令可以查看它的源代码:\n\t// go doc -src fmt Println\n\n\t// Println 是一个 exported 函数来自\n\t// \"fmt\" 包\n\n\t// Exported = 首字母大写\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go 本身不能调用 Println 函数\n\t// 这就是为什么你需要在这里调用它\n\t// Go 只能自动地调用 `func main`\n\n\t// -----\n\n\t// Go 字符串支持 Unicode 字符\n\t// 源代码同时也支持: KÖSTEBEK!\n\t//\n\t// 因为: 字面值 ~= 源代码\n\n\t// 练习: 删除下行注释的 --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// 不重要的注释:\n\t// \"Merhaba Köstebek\" 的意思是 \"你好 Gopher\"\n\t// 在土耳其语\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"first/first/main.go","url":"/github.com/inancgumus/learngo/-/blob/first/first/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"translation/spanish/02-tu-primer-programa/main.go","url":"/github.com/inancgumus/learngo/-/blob/translation/spanish/02-tu-primer-programa/main.go","content":"// Copyright © 2021 Inanc Gumus\n// Learn Go Programming Course\n// Licencia: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// Para mas tutoriales: https://learngoprogramming.com\n// Clases particulares: https://www.linkedin.com/in/inancgumus/\n// Sigueme en twitter: https://twitter.com/inancgumus\n\n// package main es un paquete especial\n// le permite a Go crear un archivo ejecutable\npackage main\n\n/*\nEsto es un comentario multilinea.\n\nla palabra import hace que otro paquete este disponible\n para este \"archivo\" .go.\n\nimport \"fmt\" te permite acceder a la funcionaliddad del paquete fmt\n en este archivo.\n*/\nimport \"fmt\"\n\n// \"func main\" es especial.\n//\n// Go tiene que saber por donde empezar\n//\n// func main crea un punto de inicio para Go\n//\n// Después de compilar el codigo,\n// Go ejecutará esta función primero.\nfunc main() {\n\t// después del: import \"fmt\"\n\t// La función Println del paquete \"fmt\" estará disponible\n\n\t// Lee sobre ella escribiendo los siguiente en la consola:\n\t// go doc -src fmt Println\n\n\t// Println es simplemente una función exportada de:\n\t// \"fmt\" package\n\n\t// Para poder exportar una función tendrás que escribir el\n\t// primer caracter del nombre de la función en mayúscula.\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go no puede llamar a la función Println por si mismo.\n\t// Por eso la tienes que llamar aqui.\n\t// Solo llama a la `func main` de forma automatica.\n\n\t// -----\n\n\t// Go soporta caracteres unicode en cadenas de texto literal\n\t// y tambien en el codigo fuente: KÖSTEBEK!\n\t//\n\t// Porque: Literal ~= Codigo Fuente\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"02-write-your-first-program/main.go","url":"/github.com/inancgumus/learngo/-/blob/02-write-your-first-program/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\t//\n\t// Because: Literal ~= Source Code\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/Go-Learning-Land/Go-Learning-Archive"},"file":{"path":"GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go","url":"/github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go","content":"// Copyright © 2021 Inanc Gumus\n// Learn Go Programming Course\n// Licencia: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// Para mas tutoriales: https://learngoprogramming.com\n// Clases particulares: https://www.linkedin.com/in/inancgumus/\n// Sigueme en twitter: https://twitter.com/inancgumus\n\n// package main es un paquete especial\n// le permite a Go crear un archivo ejecutable\npackage main\n\n/*\nEsto es un comentario multilinea.\n\nla palabra import hace que otro paquete este disponible\n para este \"archivo\" .go.\n\nimport \"fmt\" te permite acceder a la funcionaliddad del paquete fmt\n en este archivo.\n*/\nimport \"fmt\"\n\n// \"func main\" es especial.\n//\n// Go tiene que saber por donde empezar\n//\n// func main crea un punto de inicio para Go\n//\n// Despues de compilar el codigo,\n// Go ejecutara esta funcion primero.\nfunc main() {\n\t// despues del: import \"fmt\"\n\t// La funcion Println del paquete \"fmt\" estara disponible\n\n\t// Lee sobre ella escribiendo los siguiente en la consola:\n\t// go doc -src fmt Println\n\n\t// Println es simplemente una funcion exportada de:\n\t// \"fmt\" package\n\n\t// Exportada = Primera letra en mayuscula\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go no puede llamar a la funcion Println por si mismo.\n\t// Por eso la tienes que llamar aqui.\n\t// Solo llama a la `func main` de forma automatica.\n\n\t// -----\n\n\t// Go soporta caracteres unicode en cadenas de texto literal\n\t// y tambien en el codigo fuente: KÖSTEBEK!\n\t//\n\t// Porque: Literal ~= Codigo Fuente\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/Go-Learning-Land/Go-Learning-Archive"},"file":{"path":"GolangBasics/learngo/translation/chinese/02-编写第一个程序/main.go","url":"/github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main 是一个特殊的包\n// 它允许 Go 创建一个可执行文件\npackage main\n\n/*\n这是一个多行注释\n\nimport 关键字引入另一个包\n 对于这个 .go ”文件“\n\nimport \"fmt\" 允许你使用 fmt 包的各种函数\n 在这个文件\n*/\nimport \"fmt\"\n\n// \"func main\" 是特殊的\n//\n// Go 必须知道从哪里开始执行\n//\n// func main 对于 Go 而言就是开始执行的位置\n//\n// 代码编译后，\n// Go runtime 第一个执行该函数\nfunc main() {\n\t// import \"fmt\" 之后\n\t// \"fmt\" 包中的 Println 函数就可以使用\n\n\t// 在控制台输入下面的命令可以查看它的源代码:\n\t// go doc -src fmt Println\n\n\t// Println 是一个 exported 函数来自\n\t// \"fmt\" 包\n\n\t// Exported = 首字母大写\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go 本身不能调用 Println 函数\n\t// 这就是为什么你需要在这里调用它\n\t// Go 只能自动地调用 `func main`\n\n\t// -----\n\n\t// Go 字符串支持 Unicode 字符\n\t// 源代码同时也支持: KÖSTEBEK!\n\t//\n\t// 因为: 字面值 ~= 源代码\n\n\t// 练习: 删除下行注释的 --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// 不重要的注释:\n\t// \"Merhaba Köstebek\" 的意思是 \"你好 Gopher\"\n\t// 在土耳其语\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/Go-Learning-Land/Go-Learning-Archive"},"file":{"path":"GolangBasics/learngo/first/first/main.go","url":"/github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/first/first/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/Go-Learning-Land/Go-Learning-Archive"},"file":{"path":"GolangBasics/learngo/02-write-your-first-program/main.go","url":"/github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/02-write-your-first-program/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\t//\n\t// Because: Literal ~= Source Code\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/aditya43/golang-101"},"file":{"path":"002-First-Program/main.go","url":"/github.com/aditya43/golang-101/-/blob/002-First-Program/main.go","content":"// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\nimport keyword makes another package availablec for this .go \"file\".\nimport \"fmt\" lets you access fmt package''s functionality here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n// Go has to know where to start\n// func main() creates a starting point for Go\n//\n// When code is compiled, Go runtime will first run main() function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// To see ''Println'' docs, type below command in shell:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Aditya\")\n\tfmt.Println(\"नमस्ते आदित्य\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: आदित्य!\n\t//\n\t// Because: Literal ~= Source Code\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/golang/appengine"},"file":{"path":"cmd/aebundler/aebundler.go","url":"/github.com/golang/appengine/-/blob/cmd/aebundler/aebundler.go","content":"// Copyright 2015 Google Inc. All rights reserved.\n// Use of this source code is governed by the Apache 2.0\n// license that can be found in the LICENSE file.\n\n// Program aebundler turns a Go app into a fully self-contained tar file.\n// The app and its subdirectories (if any) are placed under \".\"\n// and the dependencies from $GOPATH are placed under ./_gopath/src.\n// A main func is synthesized if one does not exist.\n//\n// A sample Dockerfile to be used with this bundler could look like this:\n//\n//\tFROM gcr.io/google-appengine/go-compat\n//\tADD . /app\n//\tRUN GOPATH=/app/_gopath go build -tags appenginevm -o /app/_ah/exe\npackage main\n\nimport (\n\t\"archive/tar\"\n\t\"flag\"\n\t\"fmt\"\n\t\"go/ast\"\n\t\"go/build\"\n\t\"go/parser\"\n\t\"go/token\"\n\t\"io\"\n\t\"io/ioutil\"\n\t\"os\"\n\t\"path/filepath\"\n\t\"strings\"\n)\n\nvar (\n\toutput = flag.String(\"o\", \"\", \"name of output tar file or ''-'' for stdout\")\n\trootDir = flag.String(\"root\", \".\", \"directory name of application root\")\n\tvm = flag.Bool(\"vm\", true, `bundle an app for App Engine \"flexible environment\"`)\n\n\tskipFiles = map[string]bool{\n\t\t\".git\": true,\n\t\t\".gitconfig\": true,\n\t\t\".hg\": true,\n\t\t\".travis.yml\": true,\n\t}\n)\n\nconst (\n\tnewMain = `package main\nimport \"google.golang.org/appengine\"\nfunc main() {\n\tappengine.Main()\n}\n`\n)\n\nfunc usage() {\n\tfmt.Fprintf(os.Stderr, \"Usage of %s:\\n\", os.Args[0])\n\tfmt.Fprintf(os.Stderr, \"\\t%s -o \u003cfile.tar|-\u003e\\tBundle app to named tar file or stdout\\n\", os.Args[0])\n\tfmt.Fprintf(os.Stderr, \"\\noptional arguments:\\n\")\n\tflag.PrintDefaults()\n}\n\nfunc main() {\n\tflag.Usage = usage\n\tflag.Parse()\n\n\tvar tags []string\n\tif *vm {\n\t\ttags = append(tags, \"appenginevm\")\n\t} else {\n\t\ttags = append(tags, \"appengine\")\n\t}\n\n\ttarFile := *output\n\tif tarFile == \"\" {\n\t\tusage()\n\t\terrorf(\"Required -o flag not specified.\")\n\t}\n\n\tapp, err := analyze(tags)\n\tif err != nil {\n\t\terrorf(\"Error analyzing app: %v\", err)\n\t}\n\tif err := app.bundle(tarFile); err != nil {\n\t\terrorf(\"Unable to bundle app: %v\", err)\n\t}\n}\n\n// errorf prints the error message and exits.\nfunc errorf(format string, a ...interface{}) {\n\tfmt.Fprintf(os.Stderr, \"aebundler: \"+format+\"\\n\", a...)\n\tos.Exit(1)\n}\n\ntype app struct {\n\thasMain bool\n\tappFiles []string\n\timports map[string]string\n}\n\n// analyze checks the app for building with the given build tags and returns hasMain,\n// app files, and a map of full directory import names to original import names.\nfunc analyze(tags []string) (*app, error) {\n\tctxt := buildContext(tags)\n\thasMain, appFiles, err := checkMain(ctxt)\n\tif err != nil {\n\t\treturn nil, err\n\t}\n\tgopath := filepath.SplitList(ctxt.GOPATH)\n\tim, err := imports(ctxt, *rootDir, gopath)\n\treturn \u0026app{\n\t\thasMain: hasMain,\n\t\tappFiles: appFiles,\n\t\timports: im,\n\t}, err\n}\n\n// buildContext returns the context for building the source.\nfunc buildContext(tags []string) *build.Context {\n\treturn \u0026build.Context{\n\t\tGOARCH: build.Default.GOARCH,\n\t\tGOOS: build.Default.GOOS,\n\t\tGOROOT: build.Default.GOROOT,\n\t\tGOPATH: build.Default.GOPATH,\n\t\tCompiler: build.Default.Compiler,\n\t\tBuildTags: append(build.Default.BuildTags, tags...),\n\t}\n}\n\n// bundle bundles the app into the named tarFile (\"-\"==stdout).\nfunc (s *app) bundle(tarFile string) (err error) {\n\tvar out io.Writer\n\tif tarFile == \"-\" {\n\t\tout = os.Stdout\n\t} else {\n\t\tf, err := os.Create(tarFile)\n\t\tif err != nil {\n\t\t\treturn err\n\t\t}\n\t\tdefer func() {\n\t\t\tif cerr := f.Close(); err == nil {\n\t\t\t\terr = cerr\n\t\t\t}\n\t\t}()\n\t\tout = f\n\t}\n\ttw := tar.NewWriter(out)\n\n\tfor srcDir, importName := range s.imports {\n\t\tdstDir := \"_gopath/src/\" + importName\n\t\tif err = copyTree(tw, dstDir, srcDir); err != nil {\n\t\t\treturn fmt.Errorf(\"unable to copy directory %v to %v: %v\", srcDir, dstDir, err)\n\t\t}\n\t}\n\tif err := copyTree(tw, \".\", *rootDir); err != nil {\n\t\treturn fmt.Errorf(\"unable to copy root directory to /app: %v\", err)\n\t}\n\tif !s.hasMain {\n\t\tif err := synthesizeMain(tw, s.appFiles); err != nil {\n\t\t\treturn fmt.Errorf(\"unable to synthesize new main func: %v\", err)\n\t\t}\n\t}\n\n\tif err := tw.Close(); err != nil {\n\t\treturn fmt.Errorf(\"unable to close tar file %v: %v\", tarFile, err)\n\t}\n\treturn nil\n}\n\n// synthesizeMain generates a new main func and writes it to the tarball.\nfunc synthesizeMain(tw *tar.Writer, appFiles []string) error {\n\tappMap := make(map[string]bool)\n\tfor _, f := range appFiles {\n\t\tappMap[f] = true\n\t}\n\tvar f string\n\tfor i := 0; i \u003c 100; i++ {\n\t\tf = fmt.Sprintf(\"app_main%d.go\", i)\n\t\tif !appMap[filepath.Join(*rootDir, f)] {\n\t\t\tbreak\n\t\t}\n\t}\n\tif appMap[filepath.Join(*rootDir, f)] {\n\t\treturn fmt.Errorf(\"unable to find unique name for %v\", f)\n\t}\n\thdr := \u0026tar.Header{\n\t\tName: f,\n\t\tMode: 0644,\n\t\tSize: int64(len(newMain)),\n\t}\n\tif err := tw.WriteHeader(hdr); err != nil {\n\t\treturn fmt.Errorf(\"unable to write header for %v: %v\", f, err)\n\t}\n\tif _, err := tw.Write([]byte(newMain)); err != nil {\n\t\treturn fmt.Errorf(\"unable to write %v to tar file: %v\", f, err)\n\t}\n\treturn nil\n}\n\n// imports returns a map of all import directories (recursively) used by the app.\n// The return value maps full directory names to original import names.\nfunc imports(ctxt *build.Context, srcDir string, gopath []string) (map[string]string, error) {\n\tpkg, err := ctxt.ImportDir(srcDir, 0)\n\tif err != nil {\n\t\treturn nil, fmt.Errorf(\"unable to analyze source: %v\", err)\n\t}\n\n\t// Resolve all non-standard-library imports\n\tresult := make(map[string]string)\n\tfor _, v := range pkg.Imports {\n\t\tif !strings.Contains(v, \".\") {\n\t\t\tcontinue\n\t\t}\n\t\tsrc, err := findInGopath(v, gopath)\n\t\tif err != nil {\n\t\t\treturn nil, fmt.Errorf(\"unable to find import %v in gopath %v: %v\", v, gopath, err)\n\t\t}\n\t\tresult[src] = v\n\t\tim, err := imports(ctxt, src, gopath)\n\t\tif err != nil {\n\t\t\treturn nil, fmt.Errorf(\"unable to parse package %v: %v\", src, err)\n\t\t}\n\t\tfor k, v := range im {\n\t\t\tresult[k] = v\n\t\t}\n\t}\n\treturn result, nil\n}\n\n// findInGopath searches the gopath for the named import directory.\nfunc findInGopath(dir string, gopath []string) (string, error) {\n\tfor _, v := range gopath {\n\t\tdst := filepath.Join(v, \"src\", dir)\n\t\tif _, err := os.Stat(dst); err == nil {\n\t\t\treturn dst, nil\n\t\t}\n\t}\n\treturn \"\", fmt.Errorf(\"unable to find package %v in gopath %v\", dir, gopath)\n}\n\n// copyTree copies srcDir to tar file dstDir, ignoring skipFiles.\nfunc copyTree(tw *tar.Writer, dstDir, srcDir string) error {\n\tentries, err := ioutil.ReadDir(srcDir)\n\tif err != nil {\n\t\treturn fmt.Errorf(\"unable to read dir %v: %v\", srcDir, err)\n\t}\n\tfor _, entry := range entries {\n\t\tn := entry.Name()\n\t\tif skipFiles[n] {\n\t\t\tcontinue\n\t\t}\n\t\ts := filepath.Join(srcDir, n)\n\t\td := filepath.Join(dstDir, n)\n\t\tif entry.IsDir() {\n\t\t\tif err := copyTree(tw, d, s); err != nil {\n\t\t\t\treturn fmt.Errorf(\"unable to copy dir %v to %v: %v\", s, d, err)\n\t\t\t}\n\t\t\tcontinue\n\t\t}\n\t\tif err := copyFile(tw, d, s); err != nil {\n\t\t\treturn fmt.Errorf(\"unable to copy dir %v to %v: %v\", s, d, err)\n\t\t}\n\t}\n\treturn nil\n}\n\n// copyFile copies src to tar file dst.\nfunc copyFile(tw *tar.Writer, dst, src string) error {\n\ts, err := os.Open(src)\n\tif err != nil {\n\t\treturn fmt.Errorf(\"unable to open %v: %v\", src, err)\n\t}\n\tdefer s.Close()\n\tfi, err := s.Stat()\n\tif err != nil {\n\t\treturn fmt.Errorf(\"unable to stat %v: %v\", src, err)\n\t}\n\n\thdr, err := tar.FileInfoHeader(fi, dst)\n\tif err != nil {\n\t\treturn fmt.Errorf(\"unable to create tar header for %v: %v\", dst, err)\n\t}\n\thdr.Name = dst\n\tif err := tw.WriteHeader(hdr); err != nil {\n\t\treturn fmt.Errorf(\"unable to write header for %v: %v\", dst, err)\n\t}\n\t_, err = io.Copy(tw, s)\n\tif err != nil {\n\t\treturn fmt.Errorf(\"unable to copy %v to %v: %v\", src, dst, err)\n\t}\n\treturn nil\n}\n\n// checkMain verifies that there is a single \"main\" function.\n// It also returns a list of all Go source files in the app.\nfunc checkMain(ctxt *build.Context) (bool, []string, error) {\n\tpkg, err := ctxt.ImportDir(*rootDir, 0)\n\tif err != nil {\n\t\treturn false, nil, fmt.Errorf(\"unable to analyze source: %v\", err)\n\t}\n\tif !pkg.IsCommand() {\n\t\terrorf(\"Your app''s package needs to be changed from %q to \\\"main\\\".\\n\", pkg.Name)\n\t}\n\t// Search for a \"func main\"\n\tvar hasMain bool\n\tvar appFiles []string\n\tfor _, f := range pkg.GoFiles {\n\t\tn := filepath.Join(*rootDir, f)\n\t\tappFiles = append(appFiles, n)\n\t\tif hasMain, err = readFile(n); err != nil {\n\t\t\treturn false, nil, fmt.Errorf(\"error parsing %q: %v\", n, err)\n\t\t}\n\t}\n\treturn hasMain, appFiles, nil\n}\n\n// isMain returns whether the given function declaration is a main function.\n// Such a function must be called \"main\", not have a receiver, and have no arguments or return types.\nfunc isMain(f *ast.FuncDecl) bool {\n\tft := f.Type\n\treturn f.Name.Name == \"main\" \u0026\u0026 f.Recv == nil \u0026\u0026 ft.Params.NumFields() == 0 \u0026\u0026 ft.Results.NumFields() == 0\n}\n\n// readFile reads and parses the Go source code file and returns whether it has a main function.\nfunc readFile(filename string) (hasMain bool, err error) {\n\tvar src []byte\n\tsrc, err = ioutil.ReadFile(filename)\n\tif err != nil {\n\t\treturn\n\t}\n\tfset := token.NewFileSet()\n\tfile, err := parser.ParseFile(fset, filename, src, 0)\n\tfor _, decl := range file.Decls {\n\t\tfuncDecl, ok := decl.(*ast.FuncDecl)\n\t\tif !ok {\n\t\t\tcontinue\n\t\t}\n\t\tif !isMain(funcDecl) {\n\t\t\tcontinue\n\t\t}\n\t\thasMain = true\n\t\tbreak\n\t}\n\treturn\n}\n"},"lineMatches":[]}]}}}}'

173+ body: '{"data":{"search":{"results":{"matchCount":10,"limitHit":true,"resultCount":10,"approximateResultCount":"10+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/yinchengtsinghua/go-ethereum-chinese"},"file":{"path":"cmd/wnode/main.go","url":"/github.com/yinchengtsinghua/go-ethereum-chinese/-/blob/cmd/wnode/main.go","content":"\n//此源码被清华学神尹成大魔王专业翻译分析并修改\n//尹成QQ77025077\n//尹成微信18510341407\n//尹成所在QQ群721929980\n//尹成邮箱 yinc13@mails.tsinghua.edu.cn\n//尹成毕业于清华大学,微软区块链领域全球最有价值专家\n//https://mvp.microsoft.com/zh-cn/PublicProfile/4033620\n//版权所有2017 Go Ethereum作者\n//此文件是Go以太坊的一部分。\n//\n//Go以太坊是免费软件：您可以重新发布和/或修改它\n//根据GNU通用公共许可证的条款\n//自由软件基金会，或者许可证的第3版，或者\n//（由您选择）任何更高版本。\n//\n//Go以太坊的分布希望它会有用，\n//但没有任何保证；甚至没有\n//适销性或特定用途的适用性。见\n//GNU通用公共许可证了解更多详细信息。\n//\n//你应该已经收到一份GNU通用公共许可证的副本\n//一起去以太坊吧。如果没有，请参见\u003chttp://www.gnu.org/licenses/\u003e。\n\n//这是一个简单的耳语节点。它可以用作独立的引导节点。\n//也可用于不同的测试和诊断目的。\n\npackage main\n\nimport (\n\t\"bufio\"\n\t\"crypto/ecdsa\"\n\tcrand \"crypto/rand\"\n\t\"crypto/sha512\"\n\t\"encoding/binary\"\n\t\"encoding/hex\"\n\t\"flag\"\n\t\"fmt\"\n\t\"io/ioutil\"\n\t\"os\"\n\t\"path/filepath\"\n\t\"strconv\"\n\t\"strings\"\n\t\"time\"\n\n\t\"github.com/ethereum/go-ethereum/cmd/utils\"\n\t\"github.com/ethereum/go-ethereum/common\"\n\t\"github.com/ethereum/go-ethereum/console\"\n\t\"github.com/ethereum/go-ethereum/crypto\"\n\t\"github.com/ethereum/go-ethereum/log\"\n\t\"github.com/ethereum/go-ethereum/p2p\"\n\t\"github.com/ethereum/go-ethereum/p2p/enode\"\n\t\"github.com/ethereum/go-ethereum/p2p/nat\"\n\t\"github.com/ethereum/go-ethereum/whisper/mailserver\"\n\twhisper \"github.com/ethereum/go-ethereum/whisper/whisperv6\"\n\t\"golang.org/x/crypto/pbkdf2\"\n)\n\nconst quitCommand = \"~Q\"\nconst entropySize = 32\n\n//独生子女\nvar (\n\tserver *p2p.Server\n\tshh *whisper.Whisper\n\tdone chan struct{}\n\tmailServer mailserver.WMailServer\n\tentropy [entropySize]byte\n\n\tinput = bufio.NewReader(os.Stdin)\n)\n\n//加密\nvar (\n\tsymKey []byte\n\tpub *ecdsa.PublicKey\n\tasymKey *ecdsa.PrivateKey\n\tnodeid *ecdsa.PrivateKey\n\ttopic whisper.TopicType\n\n\tasymKeyID string\n\tasymFilterID string\n\tsymFilterID string\n\tsymPass string\n\tmsPassword string\n)\n\n//CMD参数\nvar (\n\tbootstrapMode = flag.Bool(\"standalone\", false, \"boostrap node: don''t initiate connection to peers, just wait for incoming connections\")\n\tforwarderMode = flag.Bool(\"forwarder\", false, \"forwarder mode: only forward messages, neither encrypt nor decrypt messages\")\n\tmailServerMode = flag.Bool(\"mailserver\", false, \"mail server mode: delivers expired messages on demand\")\n\trequestMail = flag.Bool(\"mailclient\", false, \"request expired messages from the bootstrap server\")\n\tasymmetricMode = flag.Bool(\"asym\", false, \"use asymmetric encryption\")\n\tgenerateKey = flag.Bool(\"generatekey\", false, \"generate and show the private key\")\n\tfileExMode = flag.Bool(\"fileexchange\", false, \"file exchange mode\")\n\tfileReader = flag.Bool(\"filereader\", false, \"load and decrypt messages saved as files, display as plain text\")\n\ttestMode = flag.Bool(\"test\", false, \"use of predefined parameters for diagnostics (password, etc.)\")\n\techoMode = flag.Bool(\"echo\", false, \"echo mode: prints some arguments for diagnostics\")\n\n\targVerbosity = flag.Int(\"verbosity\", int(log.LvlError), \"log verbosity level\")\n\targTTL = flag.Uint(\"ttl\", 30, \"time-to-live for messages in seconds\")\n\targWorkTime = flag.Uint(\"work\", 5, \"work time in seconds\")\n\targMaxSize = flag.Uint(\"maxsize\", uint(whisper.DefaultMaxMessageSize), \"max size of message\")\n\targPoW = flag.Float64(\"pow\", whisper.DefaultMinimumPoW, \"PoW for normal messages in float format (e.g. 2.7)\")\n\targServerPoW = flag.Float64(\"mspow\", whisper.DefaultMinimumPoW, \"PoW requirement for Mail Server request\")\n\n\targIP = flag.String(\"ip\", \"\", \"IP address and port of this node (e.g. 127.0.0.1:30303)\")\n\targPub = flag.String(\"pub\", \"\", \"public key for asymmetric encryption\")\n\targDBPath = flag.String(\"dbpath\", \"\", \"path to the server''s DB directory\")\n\targIDFile = flag.String(\"idfile\", \"\", \"file name with node id (private key)\")\nargEnode = flag.String(\"boot\", \"\", \"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\n\targTopic = flag.String(\"topic\", \"\", \"topic in hexadecimal format (e.g. 70a4beef)\")\n\targSaveDir = flag.String(\"savedir\", \"\", \"directory where all incoming messages will be saved as files\")\n)\n\nfunc main() {\n\tprocessArgs()\n\tinitialize()\n\trun()\n\tshutdown()\n}\n\nfunc processArgs() {\n\tflag.Parse()\n\n\tif len(*argIDFile) \u003e 0 {\n\t\tvar err error\n\t\tnodeid, err = crypto.LoadECDSA(*argIDFile)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to load file [%s]: %s.\", *argIDFile, err)\n\t\t}\n\t}\n\nconst enodePrefix = \"enode://“\n\tif len(*argEnode) \u003e 0 {\n\t\tif (*argEnode)[:len(enodePrefix)] != enodePrefix {\n\t\t\t*argEnode = enodePrefix + *argEnode\n\t\t}\n\t}\n\n\tif len(*argTopic) \u003e 0 {\n\t\tx, err := hex.DecodeString(*argTopic)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to parse the topic: %s\", err)\n\t\t}\n\t\ttopic = whisper.BytesToTopic(x)\n\t}\n\n\tif *asymmetricMode \u0026\u0026 len(*argPub) \u003e 0 {\n\t\tvar err error\n\t\tif pub, err = crypto.UnmarshalPubkey(common.FromHex(*argPub)); err != nil {\n\t\t\tutils.Fatalf(\"invalid public key\")\n\t\t}\n\t}\n\n\tif len(*argSaveDir) \u003e 0 {\n\t\tif _, err := os.Stat(*argSaveDir); os.IsNotExist(err) {\n\t\t\tutils.Fatalf(\"Download directory ''%s'' does not exist\", *argSaveDir)\n\t\t}\n\t} else if *fileExMode {\n\t\tutils.Fatalf(\"Parameter ''savedir'' is mandatory for file exchange mode\")\n\t}\n\n\tif *echoMode {\n\t\techo()\n\t}\n}\n\nfunc echo() {\n\tfmt.Printf(\"ttl = %d \\n\", *argTTL)\n\tfmt.Printf(\"workTime = %d \\n\", *argWorkTime)\n\tfmt.Printf(\"pow = %f \\n\", *argPoW)\n\tfmt.Printf(\"mspow = %f \\n\", *argServerPoW)\n\tfmt.Printf(\"ip = %s \\n\", *argIP)\n\tfmt.Printf(\"pub = %s \\n\", common.ToHex(crypto.FromECDSAPub(pub)))\n\tfmt.Printf(\"idfile = %s \\n\", *argIDFile)\n\tfmt.Printf(\"dbpath = %s \\n\", *argDBPath)\n\tfmt.Printf(\"boot = %s \\n\", *argEnode)\n}\n\nfunc initialize() {\n\tlog.Root().SetHandler(log.LvlFilterHandler(log.Lvl(*argVerbosity), log.StreamHandler(os.Stderr, log.TerminalFormat(false))))\n\n\tdone = make(chan struct{})\n\tvar peers []*enode.Node\n\tvar err error\n\n\tif *generateKey {\n\t\tkey, err := crypto.GenerateKey()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate private key: %s\", err)\n\t\t}\n\t\tk := hex.EncodeToString(crypto.FromECDSA(key))\n\t\tfmt.Printf(\"Random private key: %s \\n\", k)\n\t\tos.Exit(0)\n\t}\n\n\tif *testMode {\nsymPass = \"wwww\" //ASCII码：0x77777777\n\t\tmsPassword = \"wwww\"\n\t}\n\n\tif *bootstrapMode {\n\t\tif len(*argIP) == 0 {\n\t\t\targIP = scanLineA(\"Please enter your IP and port (e.g. 127.0.0.1:30348): \")\n\t\t}\n\t} else if *fileReader {\n\t\t*bootstrapMode = true\n\t} else {\n\t\tif len(*argEnode) == 0 {\n\t\t\targEnode = scanLineA(\"Please enter the peer''s enode: \")\n\t\t}\n\t\tpeer := enode.MustParseV4(*argEnode)\n\t\tpeers = append(peers, peer)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tcfg := \u0026whisper.Config{\n\t\tMaxMessageSize: uint32(*argMaxSize),\n\t\tMinimumAcceptedPOW: *argPoW,\n\t}\n\n\tshh = whisper.New(cfg)\n\n\tif *argPoW != whisper.DefaultMinimumPoW {\n\t\terr := shh.SetMinimumPoW(*argPoW)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set PoW: %s\", err)\n\t\t}\n\t}\n\n\tif uint32(*argMaxSize) != whisper.DefaultMaxMessageSize {\n\t\terr := shh.SetMaxMessageSize(uint32(*argMaxSize))\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set max message size: %s\", err)\n\t\t}\n\t}\n\n\tasymKeyID, err = shh.NewKeyPair()\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t}\n\n\tasymKey, err = shh.GetPrivateKey(asymKeyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t}\n\n\tif nodeid == nil {\n\t\ttmpID, err := shh.NewKeyPair()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t\t}\n\n\t\tnodeid, err = shh.GetPrivateKey(tmpID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t\t}\n\t}\n\n\tmaxPeers := 80\n\tif *bootstrapMode {\n\t\tmaxPeers = 800\n\t}\n\n\t_, err = crand.Read(entropy[:])\n\tif err != nil {\n\t\tutils.Fatalf(\"crypto/rand failed: %s\", err)\n\t}\n\n\tif *mailServerMode {\n\t\tshh.RegisterServer(\u0026mailServer)\n\t\tif err := mailServer.Init(shh, *argDBPath, msPassword, *argServerPoW); err != nil {\n\t\t\tutils.Fatalf(\"Failed to init MailServer: %s\", err)\n\t\t}\n\t}\n\n\tserver = \u0026p2p.Server{\n\t\tConfig: p2p.Config{\n\t\t\tPrivateKey: nodeid,\n\t\t\tMaxPeers: maxPeers,\n\t\t\tName: common.MakeName(\"wnode\", \"6.0\"),\n\t\t\tProtocols: shh.Protocols(),\n\t\t\tListenAddr: *argIP,\n\t\t\tNAT: nat.Any(),\n\t\t\tBootstrapNodes: peers,\n\t\t\tStaticNodes: peers,\n\t\t\tTrustedNodes: peers,\n\t\t},\n\t}\n}\n\nfunc startServer() error {\n\terr := server.Start()\n\tif err != nil {\n\t\tfmt.Printf(\"Failed to start Whisper peer: %s.\", err)\n\t\treturn err\n\t}\n\n\tfmt.Printf(\"my public key: %s \\n\", common.ToHex(crypto.FromECDSAPub(\u0026asymKey.PublicKey)))\n\tfmt.Println(server.NodeInfo().Enode)\n\n\tif *bootstrapMode {\n\t\tconfigureNode()\n\t\tfmt.Println(\"Bootstrap Whisper node started\")\n\t} else {\n\t\tfmt.Println(\"Whisper node started\")\n//首先看看我们是否可以建立连接，然后请求用户输入\n\t\twaitForConnection(true)\n\t\tconfigureNode()\n\t}\n\n\tif *fileExMode {\n\t\tfmt.Printf(\"Please type the file name to be send. To quit type: ''%s''\\n\", quitCommand)\n\t} else if *fileReader {\n\t\tfmt.Printf(\"Please type the file name to be decrypted. To quit type: ''%s''\\n\", quitCommand)\n\t} else if !*forwarderMode {\n\t\tfmt.Printf(\"Please type the message. To quit type: ''%s''\\n\", quitCommand)\n\t}\n\treturn nil\n}\n\nfunc configureNode() {\n\tvar err error\n\tvar p2pAccept bool\n\n\tif *forwarderMode {\n\t\treturn\n\t}\n\n\tif *asymmetricMode {\n\t\tif len(*argPub) == 0 {\n\t\t\ts := scanLine(\"Please enter the peer''s public key: \")\n\t\t\tb := common.FromHex(s)\n\t\t\tif b == nil {\n\t\t\t\tutils.Fatalf(\"Error: can not convert hexadecimal string\")\n\t\t\t}\n\t\t\tif pub, err = crypto.UnmarshalPubkey(b); err != nil {\n\t\t\t\tutils.Fatalf(\"Error: invalid peer public key\")\n\t\t\t}\n\t\t}\n\t}\n\n\tif *requestMail {\n\t\tp2pAccept = true\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tif !*asymmetricMode \u0026\u0026 !*forwarderMode {\n\t\tif len(symPass) == 0 {\n\t\t\tsymPass, err = console.Stdin.PromptPassword(\"Please enter the password for symmetric encryption: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read passphrase: %v\", err)\n\t\t\t}\n\t\t}\n\n\t\tsymKeyID, err := shh.AddSymKeyFromPassword(symPass)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to create symmetric key: %s\", err)\n\t\t}\n\t\tsymKey, err = shh.GetSymKey(symKeyID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to save symmetric key: %s\", err)\n\t\t}\n\t\tif len(*argTopic) == 0 {\n\t\t\tgenerateTopic([]byte(symPass))\n\t\t}\n\n\t\tfmt.Printf(\"Filter is configured for the topic: %x \\n\", topic)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(*argDBPath) == 0 {\n\t\t\targDBPath = scanLineA(\"Please enter the path to DB file: \")\n\t\t}\n\t}\n\n\tsymFilter := whisper.Filter{\n\t\tKeySym: symKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tsymFilterID, err = shh.Subscribe(\u0026symFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n\n\tasymFilter := whisper.Filter{\n\t\tKeyAsym: asymKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tasymFilterID, err = shh.Subscribe(\u0026asymFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n}\n\nfunc generateTopic(password []byte) {\n\tx := pbkdf2.Key(password, password, 4096, 128, sha512.New)\n\tfor i := 0; i \u003c len(x); i++ {\n\t\ttopic[i%whisper.TopicLength] ^= x[i]\n\t}\n}\n\nfunc waitForConnection(timeout bool) {\n\tvar cnt int\n\tvar connected bool\n\tfor !connected {\n\t\ttime.Sleep(time.Millisecond * 50)\n\t\tconnected = server.PeerCount() \u003e 0\n\t\tif timeout {\n\t\t\tcnt++\n\t\t\tif cnt \u003e 1000 {\n\t\t\t\tutils.Fatalf(\"Timeout expired, failed to connect\")\n\t\t\t}\n\t\t}\n\t}\n\n\tfmt.Println(\"Connected to peer.\")\n}\n\nfunc run() {\n\terr := startServer()\n\tif err != nil {\n\t\treturn\n\t}\n\tdefer server.Stop()\n\tshh.Start(nil)\n\tdefer shh.Stop()\n\n\tif !*forwarderMode {\n\t\tgo messageLoop()\n\t}\n\n\tif *requestMail {\n\t\trequestExpiredMessagesLoop()\n\t} else if *fileExMode {\n\t\tsendFilesLoop()\n\t} else if *fileReader {\n\t\tfileReaderLoop()\n\t} else {\n\t\tsendLoop()\n\t}\n}\n\nfunc shutdown() {\n\tclose(done)\n\tmailServer.Close()\n}\n\nfunc sendLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tsendMsg([]byte(s))\n\t\tif *asymmetricMode {\n//为方便起见，请打印您自己的消息，\n//因为在非对称模式下是不可能解密的\n\t\t\ttimestamp := time.Now().Unix()\n\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: %s\\n\", timestamp, from, s)\n\t\t}\n\t}\n}\n\nfunc sendFilesLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tb, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\n\t\t\th := sendMsg(b)\n\t\t\tif (h == common.Hash{}) {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: message was not sent \\n\")\n\t\t\t} else {\n\t\t\t\ttimestamp := time.Now().Unix()\n\t\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: sent message with hash %x\\n\", timestamp, from, h)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc fileReaderLoop() {\n\twatcher1 := shh.GetFilter(symFilterID)\n\twatcher2 := shh.GetFilter(asymFilterID)\n\tif watcher1 == nil \u0026\u0026 watcher2 == nil {\n\t\tfmt.Println(\"Error: neither symmetric nor asymmetric filter is installed\")\n\t\treturn\n\t}\n\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\traw, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\nenv := whisper.Envelope{Data: raw} //主题为零\nmsg := env.Open(watcher1) //不管主题如何，都强制打开信封\n\t\t\tif msg == nil {\n\t\t\t\tmsg = env.Open(watcher2)\n\t\t\t}\n\t\t\tif msg == nil {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: failed to decrypt the message \\n\")\n\t\t\t} else {\n\t\t\t\tprintMessageInfo(msg)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc scanLine(prompt string) string {\n\tif len(prompt) \u003e 0 {\n\t\tfmt.Print(prompt)\n\t}\n\ttxt, err := input.ReadString(''\\n'')\n\tif err != nil {\n\t\tutils.Fatalf(\"input error: %s\", err)\n\t}\n\ttxt = strings.TrimRight(txt, \"\\n\\r\")\n\treturn txt\n}\n\nfunc scanLineA(prompt string) *string {\n\ts := scanLine(prompt)\n\treturn \u0026s\n}\n\nfunc scanUint(prompt string) uint32 {\n\ts := scanLine(prompt)\n\ti, err := strconv.Atoi(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Fail to parse the lower time limit: %s\", err)\n\t}\n\treturn uint32(i)\n}\n\nfunc sendMsg(payload []byte) common.Hash {\n\tparams := whisper.MessageParams{\n\t\tSrc: asymKey,\n\t\tDst: pub,\n\t\tKeySym: symKey,\n\t\tPayload: payload,\n\t\tTopic: topic,\n\t\tTTL: uint32(*argTTL),\n\t\tPoW: *argPoW,\n\t\tWorkTime: uint32(*argWorkTime),\n\t}\n\n\tmsg, err := whisper.NewSentMessage(\u0026params)\n\tif err != nil {\n\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t}\n\n\tenvelope, err := msg.Wrap(\u0026params)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to seal message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\terr = shh.Send(envelope)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to send message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\treturn envelope.Hash()\n}\n\nfunc messageLoop() {\n\tsf := shh.GetFilter(symFilterID)\n\tif sf == nil {\n\t\tutils.Fatalf(\"symmetric filter is not installed\")\n\t}\n\n\taf := shh.GetFilter(asymFilterID)\n\tif af == nil {\n\t\tutils.Fatalf(\"asymmetric filter is not installed\")\n\t}\n\n\tticker := time.NewTicker(time.Millisecond * 50)\n\n\tfor {\n\t\tselect {\n\t\tcase \u003c-ticker.C:\n\t\t\tm1 := sf.Retrieve()\n\t\t\tm2 := af.Retrieve()\n\t\t\tmessages := append(m1, m2...)\n\t\t\tfor _, msg := range messages {\n\t\t\t\treportedOnce := false\n\t\t\t\tif !*fileExMode \u0026\u0026 len(msg.Payload) \u003c= 2048 {\n\t\t\t\t\tprintMessageInfo(msg)\n\t\t\t\t\treportedOnce = true\n\t\t\t\t}\n\n//在指定argsavedir时保存所有消息。\n//FileExMode仅指定消息保存后如何显示在控制台上。\n//如果fileexmode==true，则只显示哈希值，因为消息可能太大。\n\t\t\t\tif len(*argSaveDir) \u003e 0 {\n\t\t\t\t\twriteMessageToFile(*argSaveDir, msg, !reportedOnce)\n\t\t\t\t}\n\t\t\t}\n\t\tcase \u003c-done:\n\t\t\treturn\n\t\t}\n\t}\n}\n\nfunc printMessageInfo(msg *whisper.ReceivedMessage) {\ntimestamp := fmt.Sprintf(\"%d\", msg.Sent) //用于诊断的Unix时间戳\n\ttext := string(msg.Payload)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tif whisper.IsPubKeyEqual(msg.Src, \u0026asymKey.PublicKey) {\nfmt.Printf(\"\\n%s \u003c%x\u003e: %s\\n\", timestamp, address, text) //我的信息\n\t} else {\nfmt.Printf(\"\\n%s [%x]: %s\\n\", timestamp, address, text) //来自对等方的消息\n\t}\n}\n\nfunc writeMessageToFile(dir string, msg *whisper.ReceivedMessage, show bool) {\n\tif len(dir) == 0 {\n\t\treturn\n\t}\n\n\ttimestamp := fmt.Sprintf(\"%d\", msg.Sent)\n\tname := fmt.Sprintf(\"%x\", msg.EnvelopeHash)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tenv := shh.GetEnvelope(msg.EnvelopeHash)\n\tif env == nil {\n\t\tfmt.Printf(\"\\nUnexpected error: envelope not found: %x\\n\", msg.EnvelopeHash)\n\t\treturn\n\t}\n\n//这是一个示例代码；如果不想保存自己的消息，请取消注释。\n//如果whisper.ispubkeyequal（msg.src，\u0026asymkey.publickey）\n//fmt.printf（“\\n%s\u003c%x\u003e：我收到的消息，未保存：“%s''\\n”，时间戳，地址，名称）\n//返回\n//}\n\n\tfullpath := filepath.Join(dir, name)\n\terr := ioutil.WriteFile(fullpath, env.Data, 0644)\n\tif err != nil {\n\t\tfmt.Printf(\"\\n%s {%x}: message received but not saved: %s\\n\", timestamp, address, err)\n\t} else if show {\n\t\tfmt.Printf(\"\\n%s {%x}: message received and saved as ''%s'' (%d bytes)\\n\", timestamp, address, name, len(env.Data))\n\t}\n}\n\nfunc requestExpiredMessagesLoop() {\n\tvar key, peerID, bloom []byte\n\tvar timeLow, timeUpp uint32\n\tvar t string\n\tvar xt whisper.TopicType\n\n\tkeyID, err := shh.AddSymKeyFromPassword(msPassword)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to create symmetric key for mail request: %s\", err)\n\t}\n\tkey, err = shh.GetSymKey(keyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to save symmetric key for mail request: %s\", err)\n\t}\n\tpeerID = extractIDFromEnode(*argEnode)\n\tshh.AllowP2PMessagesFromPeer(peerID)\n\n\tfor {\n\t\ttimeLow = scanUint(\"Please enter the lower limit of the time range (unix timestamp): \")\n\t\ttimeUpp = scanUint(\"Please enter the upper limit of the time range (unix timestamp): \")\n\t\tt = scanLine(\"Enter the topic (hex). Press enter to request all messages, regardless of the topic: \")\n\t\tif len(t) == whisper.TopicLength*2 {\n\t\t\tx, err := hex.DecodeString(t)\n\t\t\tif err != nil {\n\t\t\t\tfmt.Printf(\"Failed to parse the topic: %s \\n\", err)\n\t\t\t\tcontinue\n\t\t\t}\n\t\t\txt = whisper.BytesToTopic(x)\n\t\t\tbloom = whisper.TopicToBloom(xt)\n\t\t\tobfuscateBloom(bloom)\n\t\t} else if len(t) == 0 {\n\t\t\tbloom = whisper.MakeFullNodeBloom()\n\t\t} else {\n\t\t\tfmt.Println(\"Error: topic is invalid, request aborted\")\n\t\t\tcontinue\n\t\t}\n\n\t\tif timeUpp == 0 {\n\t\t\ttimeUpp = 0xFFFFFFFF\n\t\t}\n\n\t\tdata := make([]byte, 8, 8+whisper.BloomFilterSize)\n\t\tbinary.BigEndian.PutUint32(data, timeLow)\n\t\tbinary.BigEndian.PutUint32(data[4:], timeUpp)\n\t\tdata = append(data, bloom...)\n\n\t\tvar params whisper.MessageParams\n\t\tparams.PoW = *argServerPoW\n\t\tparams.Payload = data\n\t\tparams.KeySym = key\n\t\tparams.Src = asymKey\n\t\tparams.WorkTime = 5\n\n\t\tmsg, err := whisper.NewSentMessage(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t\t}\n\t\tenv, err := msg.Wrap(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Wrap failed: %s\", err)\n\t\t}\n\n\t\terr = shh.RequestHistoricMessages(peerID, env)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to send P2P message: %s\", err)\n\t\t}\n\n\t\ttime.Sleep(time.Second * 5)\n\t}\n}\n\nfunc extractIDFromEnode(s string) []byte {\n\tn, err := enode.ParseV4(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to parse enode: %s\", err)\n\t}\n\treturn n.ID().Bytes()\n}\n\n//模糊布卢姆增加16个随机位到布卢姆\n//筛选，以便混淆包含的主题。\n//它在每个会话中都具有确定性。\n//尽管有额外的位，它将平均匹配\n//比完整节点的Bloom过滤器少32000倍的消息。\nfunc obfuscateBloom(bloom []byte) {\n\tconst half = entropySize / 2\n\tfor i := 0; i \u003c half; i++ {\n\t\tx := int(entropy[i])\n\t\tif entropy[half+i] \u003c 128 {\n\t\t\tx += 256\n\t\t}\n\nbloom[x/8] = 1 \u003c\u003c uint(x%8) //设置位号x\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":116,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum"},"file":{"path":"cmd/wnode/main.go","url":"/github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/-/blob/cmd/wnode/main.go","content":"\n//此源码被清华学神尹成大魔王专业翻译分析并修改\n//尹成QQ77025077\n//尹成微信18510341407\n//尹成所在QQ群721929980\n//尹成邮箱 yinc13@mails.tsinghua.edu.cn\n//尹成毕业于清华大学,微软区块链领域全球最有价值专家\n//https://mvp.microsoft.com/zh-cn/PublicProfile/4033620\n//版权所有2017 Go Ethereum作者\n//此文件是Go以太坊的一部分。\n//\n//Go以太坊是免费软件：您可以重新发布和/或修改它\n//根据GNU通用公共许可证的条款\n//自由软件基金会，或者许可证的第3版，或者\n//（由您选择）任何更高版本。\n//\n//Go以太坊的分布希望它会有用，\n//但没有任何保证；甚至没有\n//适销性或特定用途的适用性。见\n//GNU通用公共许可证了解更多详细信息。\n//\n//你应该已经收到一份GNU通用公共许可证的副本\n//一起去以太坊吧。如果没有，请参见\u003chttp://www.gnu.org/licenses/\u003e。\n\n//这是一个简单的耳语节点。它可以用作独立的引导节点。\n//也可用于不同的测试和诊断目的。\n\npackage main\n\nimport (\n\t\"bufio\"\n\t\"crypto/ecdsa\"\n\tcrand \"crypto/rand\"\n\t\"crypto/sha512\"\n\t\"encoding/binary\"\n\t\"encoding/hex\"\n\t\"flag\"\n\t\"fmt\"\n\t\"io/ioutil\"\n\t\"os\"\n\t\"path/filepath\"\n\t\"strconv\"\n\t\"strings\"\n\t\"time\"\n\n\t\"github.com/ethereum/go-ethereum/cmd/utils\"\n\t\"github.com/ethereum/go-ethereum/common\"\n\t\"github.com/ethereum/go-ethereum/console\"\n\t\"github.com/ethereum/go-ethereum/crypto\"\n\t\"github.com/ethereum/go-ethereum/log\"\n\t\"github.com/ethereum/go-ethereum/p2p\"\n\t\"github.com/ethereum/go-ethereum/p2p/discover\"\n\t\"github.com/ethereum/go-ethereum/p2p/nat\"\n\t\"github.com/ethereum/go-ethereum/whisper/mailserver\"\n\twhisper \"github.com/ethereum/go-ethereum/whisper/whisperv6\"\n\t\"golang.org/x/crypto/pbkdf2\"\n)\n\nconst quitCommand = \"~Q\"\nconst entropySize = 32\n\n//独生子女\nvar (\n\tserver *p2p.Server\n\tshh *whisper.Whisper\n\tdone chan struct{}\n\tmailServer mailserver.WMailServer\n\tentropy [entropySize]byte\n\n\tinput = bufio.NewReader(os.Stdin)\n)\n\n//加密\nvar (\n\tsymKey []byte\n\tpub *ecdsa.PublicKey\n\tasymKey *ecdsa.PrivateKey\n\tnodeid *ecdsa.PrivateKey\n\ttopic whisper.TopicType\n\n\tasymKeyID string\n\tasymFilterID string\n\tsymFilterID string\n\tsymPass string\n\tmsPassword string\n)\n\n//CMD参数\nvar (\n\tbootstrapMode = flag.Bool(\"standalone\", false, \"boostrap node: don''t initiate connection to peers, just wait for incoming connections\")\n\tforwarderMode = flag.Bool(\"forwarder\", false, \"forwarder mode: only forward messages, neither encrypt nor decrypt messages\")\n\tmailServerMode = flag.Bool(\"mailserver\", false, \"mail server mode: delivers expired messages on demand\")\n\trequestMail = flag.Bool(\"mailclient\", false, \"request expired messages from the bootstrap server\")\n\tasymmetricMode = flag.Bool(\"asym\", false, \"use asymmetric encryption\")\n\tgenerateKey = flag.Bool(\"generatekey\", false, \"generate and show the private key\")\n\tfileExMode = flag.Bool(\"fileexchange\", false, \"file exchange mode\")\n\tfileReader = flag.Bool(\"filereader\", false, \"load and decrypt messages saved as files, display as plain text\")\n\ttestMode = flag.Bool(\"test\", false, \"use of predefined parameters for diagnostics (password, etc.)\")\n\techoMode = flag.Bool(\"echo\", false, \"echo mode: prints some arguments for diagnostics\")\n\n\targVerbosity = flag.Int(\"verbosity\", int(log.LvlError), \"log verbosity level\")\n\targTTL = flag.Uint(\"ttl\", 30, \"time-to-live for messages in seconds\")\n\targWorkTime = flag.Uint(\"work\", 5, \"work time in seconds\")\n\targMaxSize = flag.Uint(\"maxsize\", uint(whisper.DefaultMaxMessageSize), \"max size of message\")\n\targPoW = flag.Float64(\"pow\", whisper.DefaultMinimumPoW, \"PoW for normal messages in float format (e.g. 2.7)\")\n\targServerPoW = flag.Float64(\"mspow\", whisper.DefaultMinimumPoW, \"PoW requirement for Mail Server request\")\n\n\targIP = flag.String(\"ip\", \"\", \"IP address and port of this node (e.g. 127.0.0.1:30303)\")\n\targPub = flag.String(\"pub\", \"\", \"public key for asymmetric encryption\")\n\targDBPath = flag.String(\"dbpath\", \"\", \"path to the server''s DB directory\")\n\targIDFile = flag.String(\"idfile\", \"\", \"file name with node id (private key)\")\nargEnode = flag.String(\"boot\", \"\", \"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\n\targTopic = flag.String(\"topic\", \"\", \"topic in hexadecimal format (e.g. 70a4beef)\")\n\targSaveDir = flag.String(\"savedir\", \"\", \"directory where all incoming messages will be saved as files\")\n)\n\nfunc main() {\n\tprocessArgs()\n\tinitialize()\n\trun()\n\tshutdown()\n}\n\nfunc processArgs() {\n\tflag.Parse()\n\n\tif len(*argIDFile) \u003e 0 {\n\t\tvar err error\n\t\tnodeid, err = crypto.LoadECDSA(*argIDFile)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to load file [%s]: %s.\", *argIDFile, err)\n\t\t}\n\t}\n\nconst enodePrefix = \"enode://“\n\tif len(*argEnode) \u003e 0 {\n\t\tif (*argEnode)[:len(enodePrefix)] != enodePrefix {\n\t\t\t*argEnode = enodePrefix + *argEnode\n\t\t}\n\t}\n\n\tif len(*argTopic) \u003e 0 {\n\t\tx, err := hex.DecodeString(*argTopic)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to parse the topic: %s\", err)\n\t\t}\n\t\ttopic = whisper.BytesToTopic(x)\n\t}\n\n\tif *asymmetricMode \u0026\u0026 len(*argPub) \u003e 0 {\n\t\tvar err error\n\t\tif pub, err = crypto.UnmarshalPubkey(common.FromHex(*argPub)); err != nil {\n\t\t\tutils.Fatalf(\"invalid public key\")\n\t\t}\n\t}\n\n\tif len(*argSaveDir) \u003e 0 {\n\t\tif _, err := os.Stat(*argSaveDir); os.IsNotExist(err) {\n\t\t\tutils.Fatalf(\"Download directory ''%s'' does not exist\", *argSaveDir)\n\t\t}\n\t} else if *fileExMode {\n\t\tutils.Fatalf(\"Parameter ''savedir'' is mandatory for file exchange mode\")\n\t}\n\n\tif *echoMode {\n\t\techo()\n\t}\n}\n\nfunc echo() {\n\tfmt.Printf(\"ttl = %d \\n\", *argTTL)\n\tfmt.Printf(\"workTime = %d \\n\", *argWorkTime)\n\tfmt.Printf(\"pow = %f \\n\", *argPoW)\n\tfmt.Printf(\"mspow = %f \\n\", *argServerPoW)\n\tfmt.Printf(\"ip = %s \\n\", *argIP)\n\tfmt.Printf(\"pub = %s \\n\", common.ToHex(crypto.FromECDSAPub(pub)))\n\tfmt.Printf(\"idfile = %s \\n\", *argIDFile)\n\tfmt.Printf(\"dbpath = %s \\n\", *argDBPath)\n\tfmt.Printf(\"boot = %s \\n\", *argEnode)\n}\n\nfunc initialize() {\n\tlog.Root().SetHandler(log.LvlFilterHandler(log.Lvl(*argVerbosity), log.StreamHandler(os.Stderr, log.TerminalFormat(false))))\n\n\tdone = make(chan struct{})\n\tvar peers []*discover.Node\n\tvar err error\n\n\tif *generateKey {\n\t\tkey, err := crypto.GenerateKey()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate private key: %s\", err)\n\t\t}\n\t\tk := hex.EncodeToString(crypto.FromECDSA(key))\n\t\tfmt.Printf(\"Random private key: %s \\n\", k)\n\t\tos.Exit(0)\n\t}\n\n\tif *testMode {\nsymPass = \"wwww\" //ASCII码：0x77777777\n\t\tmsPassword = \"wwww\"\n\t}\n\n\tif *bootstrapMode {\n\t\tif len(*argIP) == 0 {\n\t\t\targIP = scanLineA(\"Please enter your IP and port (e.g. 127.0.0.1:30348): \")\n\t\t}\n\t} else if *fileReader {\n\t\t*bootstrapMode = true\n\t} else {\n\t\tif len(*argEnode) == 0 {\n\t\t\targEnode = scanLineA(\"Please enter the peer''s enode: \")\n\t\t}\n\t\tpeer := discover.MustParseNode(*argEnode)\n\t\tpeers = append(peers, peer)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tcfg := \u0026whisper.Config{\n\t\tMaxMessageSize: uint32(*argMaxSize),\n\t\tMinimumAcceptedPOW: *argPoW,\n\t}\n\n\tshh = whisper.New(cfg)\n\n\tif *argPoW != whisper.DefaultMinimumPoW {\n\t\terr := shh.SetMinimumPoW(*argPoW)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set PoW: %s\", err)\n\t\t}\n\t}\n\n\tif uint32(*argMaxSize) != whisper.DefaultMaxMessageSize {\n\t\terr := shh.SetMaxMessageSize(uint32(*argMaxSize))\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set max message size: %s\", err)\n\t\t}\n\t}\n\n\tasymKeyID, err = shh.NewKeyPair()\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t}\n\n\tasymKey, err = shh.GetPrivateKey(asymKeyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t}\n\n\tif nodeid == nil {\n\t\ttmpID, err := shh.NewKeyPair()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t\t}\n\n\t\tnodeid, err = shh.GetPrivateKey(tmpID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t\t}\n\t}\n\n\tmaxPeers := 80\n\tif *bootstrapMode {\n\t\tmaxPeers = 800\n\t}\n\n\t_, err = crand.Read(entropy[:])\n\tif err != nil {\n\t\tutils.Fatalf(\"crypto/rand failed: %s\", err)\n\t}\n\n\tif *mailServerMode {\n\t\tshh.RegisterServer(\u0026mailServer)\n\t\tif err := mailServer.Init(shh, *argDBPath, msPassword, *argServerPoW); err != nil {\n\t\t\tutils.Fatalf(\"Failed to init MailServer: %s\", err)\n\t\t}\n\t}\n\n\tserver = \u0026p2p.Server{\n\t\tConfig: p2p.Config{\n\t\t\tPrivateKey: nodeid,\n\t\t\tMaxPeers: maxPeers,\n\t\t\tName: common.MakeName(\"wnode\", \"6.0\"),\n\t\t\tProtocols: shh.Protocols(),\n\t\t\tListenAddr: *argIP,\n\t\t\tNAT: nat.Any(),\n\t\t\tBootstrapNodes: peers,\n\t\t\tStaticNodes: peers,\n\t\t\tTrustedNodes: peers,\n\t\t},\n\t}\n}\n\nfunc startServer() error {\n\terr := server.Start()\n\tif err != nil {\n\t\tfmt.Printf(\"Failed to start Whisper peer: %s.\", err)\n\t\treturn err\n\t}\n\n\tfmt.Printf(\"my public key: %s \\n\", common.ToHex(crypto.FromECDSAPub(\u0026asymKey.PublicKey)))\n\tfmt.Println(server.NodeInfo().Enode)\n\n\tif *bootstrapMode {\n\t\tconfigureNode()\n\t\tfmt.Println(\"Bootstrap Whisper node started\")\n\t} else {\n\t\tfmt.Println(\"Whisper node started\")\n//首先看看我们是否可以建立连接，然后请求用户输入\n\t\twaitForConnection(true)\n\t\tconfigureNode()\n\t}\n\n\tif *fileExMode {\n\t\tfmt.Printf(\"Please type the file name to be send. To quit type: ''%s''\\n\", quitCommand)\n\t} else if *fileReader {\n\t\tfmt.Printf(\"Please type the file name to be decrypted. To quit type: ''%s''\\n\", quitCommand)\n\t} else if !*forwarderMode {\n\t\tfmt.Printf(\"Please type the message. To quit type: ''%s''\\n\", quitCommand)\n\t}\n\treturn nil\n}\n\nfunc configureNode() {\n\tvar err error\n\tvar p2pAccept bool\n\n\tif *forwarderMode {\n\t\treturn\n\t}\n\n\tif *asymmetricMode {\n\t\tif len(*argPub) == 0 {\n\t\t\ts := scanLine(\"Please enter the peer''s public key: \")\n\t\t\tb := common.FromHex(s)\n\t\t\tif b == nil {\n\t\t\t\tutils.Fatalf(\"Error: can not convert hexadecimal string\")\n\t\t\t}\n\t\t\tif pub, err = crypto.UnmarshalPubkey(b); err != nil {\n\t\t\t\tutils.Fatalf(\"Error: invalid peer public key\")\n\t\t\t}\n\t\t}\n\t}\n\n\tif *requestMail {\n\t\tp2pAccept = true\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tif !*asymmetricMode \u0026\u0026 !*forwarderMode {\n\t\tif len(symPass) == 0 {\n\t\t\tsymPass, err = console.Stdin.PromptPassword(\"Please enter the password for symmetric encryption: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read passphrase: %v\", err)\n\t\t\t}\n\t\t}\n\n\t\tsymKeyID, err := shh.AddSymKeyFromPassword(symPass)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to create symmetric key: %s\", err)\n\t\t}\n\t\tsymKey, err = shh.GetSymKey(symKeyID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to save symmetric key: %s\", err)\n\t\t}\n\t\tif len(*argTopic) == 0 {\n\t\t\tgenerateTopic([]byte(symPass))\n\t\t}\n\n\t\tfmt.Printf(\"Filter is configured for the topic: %x \\n\", topic)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(*argDBPath) == 0 {\n\t\t\targDBPath = scanLineA(\"Please enter the path to DB file: \")\n\t\t}\n\t}\n\n\tsymFilter := whisper.Filter{\n\t\tKeySym: symKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tsymFilterID, err = shh.Subscribe(\u0026symFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n\n\tasymFilter := whisper.Filter{\n\t\tKeyAsym: asymKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tasymFilterID, err = shh.Subscribe(\u0026asymFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n}\n\nfunc generateTopic(password []byte) {\n\tx := pbkdf2.Key(password, password, 4096, 128, sha512.New)\n\tfor i := 0; i \u003c len(x); i++ {\n\t\ttopic[i%whisper.TopicLength] ^= x[i]\n\t}\n}\n\nfunc waitForConnection(timeout bool) {\n\tvar cnt int\n\tvar connected bool\n\tfor !connected {\n\t\ttime.Sleep(time.Millisecond * 50)\n\t\tconnected = server.PeerCount() \u003e 0\n\t\tif timeout {\n\t\t\tcnt++\n\t\t\tif cnt \u003e 1000 {\n\t\t\t\tutils.Fatalf(\"Timeout expired, failed to connect\")\n\t\t\t}\n\t\t}\n\t}\n\n\tfmt.Println(\"Connected to peer.\")\n}\n\nfunc run() {\n\terr := startServer()\n\tif err != nil {\n\t\treturn\n\t}\n\tdefer server.Stop()\n\tshh.Start(nil)\n\tdefer shh.Stop()\n\n\tif !*forwarderMode {\n\t\tgo messageLoop()\n\t}\n\n\tif *requestMail {\n\t\trequestExpiredMessagesLoop()\n\t} else if *fileExMode {\n\t\tsendFilesLoop()\n\t} else if *fileReader {\n\t\tfileReaderLoop()\n\t} else {\n\t\tsendLoop()\n\t}\n}\n\nfunc shutdown() {\n\tclose(done)\n\tmailServer.Close()\n}\n\nfunc sendLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tsendMsg([]byte(s))\n\t\tif *asymmetricMode {\n//为方便起见，请打印您自己的消息，\n//因为在非对称模式下是不可能解密的\n\t\t\ttimestamp := time.Now().Unix()\n\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: %s\\n\", timestamp, from, s)\n\t\t}\n\t}\n}\n\nfunc sendFilesLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tb, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\n\t\t\th := sendMsg(b)\n\t\t\tif (h == common.Hash{}) {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: message was not sent \\n\")\n\t\t\t} else {\n\t\t\t\ttimestamp := time.Now().Unix()\n\t\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: sent message with hash %x\\n\", timestamp, from, h)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc fileReaderLoop() {\n\twatcher1 := shh.GetFilter(symFilterID)\n\twatcher2 := shh.GetFilter(asymFilterID)\n\tif watcher1 == nil \u0026\u0026 watcher2 == nil {\n\t\tfmt.Println(\"Error: neither symmetric nor asymmetric filter is installed\")\n\t\treturn\n\t}\n\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\traw, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\nenv := whisper.Envelope{Data: raw} //主题为零\nmsg := env.Open(watcher1) //不管主题如何，都强制打开信封\n\t\t\tif msg == nil {\n\t\t\t\tmsg = env.Open(watcher2)\n\t\t\t}\n\t\t\tif msg == nil {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: failed to decrypt the message \\n\")\n\t\t\t} else {\n\t\t\t\tprintMessageInfo(msg)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc scanLine(prompt string) string {\n\tif len(prompt) \u003e 0 {\n\t\tfmt.Print(prompt)\n\t}\n\ttxt, err := input.ReadString(''\\n'')\n\tif err != nil {\n\t\tutils.Fatalf(\"input error: %s\", err)\n\t}\n\ttxt = strings.TrimRight(txt, \"\\n\\r\")\n\treturn txt\n}\n\nfunc scanLineA(prompt string) *string {\n\ts := scanLine(prompt)\n\treturn \u0026s\n}\n\nfunc scanUint(prompt string) uint32 {\n\ts := scanLine(prompt)\n\ti, err := strconv.Atoi(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Fail to parse the lower time limit: %s\", err)\n\t}\n\treturn uint32(i)\n}\n\nfunc sendMsg(payload []byte) common.Hash {\n\tparams := whisper.MessageParams{\n\t\tSrc: asymKey,\n\t\tDst: pub,\n\t\tKeySym: symKey,\n\t\tPayload: payload,\n\t\tTopic: topic,\n\t\tTTL: uint32(*argTTL),\n\t\tPoW: *argPoW,\n\t\tWorkTime: uint32(*argWorkTime),\n\t}\n\n\tmsg, err := whisper.NewSentMessage(\u0026params)\n\tif err != nil {\n\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t}\n\n\tenvelope, err := msg.Wrap(\u0026params)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to seal message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\terr = shh.Send(envelope)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to send message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\treturn envelope.Hash()\n}\n\nfunc messageLoop() {\n\tsf := shh.GetFilter(symFilterID)\n\tif sf == nil {\n\t\tutils.Fatalf(\"symmetric filter is not installed\")\n\t}\n\n\taf := shh.GetFilter(asymFilterID)\n\tif af == nil {\n\t\tutils.Fatalf(\"asymmetric filter is not installed\")\n\t}\n\n\tticker := time.NewTicker(time.Millisecond * 50)\n\n\tfor {\n\t\tselect {\n\t\tcase \u003c-ticker.C:\n\t\t\tm1 := sf.Retrieve()\n\t\t\tm2 := af.Retrieve()\n\t\t\tmessages := append(m1, m2...)\n\t\t\tfor _, msg := range messages {\n\t\t\t\treportedOnce := false\n\t\t\t\tif !*fileExMode \u0026\u0026 len(msg.Payload) \u003c= 2048 {\n\t\t\t\t\tprintMessageInfo(msg)\n\t\t\t\t\treportedOnce = true\n\t\t\t\t}\n\n//在指定argsavedir时保存所有消息。\n//\n//如果fileexmode==true，则只显示哈希值，因为消息可能太大。\n\t\t\t\tif len(*argSaveDir) \u003e 0 {\n\t\t\t\t\twriteMessageToFile(*argSaveDir, msg, !reportedOnce)\n\t\t\t\t}\n\t\t\t}\n\t\tcase \u003c-done:\n\t\t\treturn\n\t\t}\n\t}\n}\n\nfunc printMessageInfo(msg *whisper.ReceivedMessage) {\ntimestamp := fmt.Sprintf(\"%d\", msg.Sent) //用于诊断的Unix时间戳\n\ttext := string(msg.Payload)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tif whisper.IsPubKeyEqual(msg.Src, \u0026asymKey.PublicKey) {\nfmt.Printf(\"\\n%s \u003c%x\u003e: %s\\n\", timestamp, address, text) //我的信息\n\t} else {\nfmt.Printf(\"\\n%s [%x]: %s\\n\", timestamp, address, text) //\n\t}\n}\n\nfunc writeMessageToFile(dir string, msg *whisper.ReceivedMessage, show bool) {\n\tif len(dir) == 0 {\n\t\treturn\n\t}\n\n\ttimestamp := fmt.Sprintf(\"%d\", msg.Sent)\n\tname := fmt.Sprintf(\"%x\", msg.EnvelopeHash)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tenv := shh.GetEnvelope(msg.EnvelopeHash)\n\tif env == nil {\n\t\tfmt.Printf(\"\\nUnexpected error: envelope not found: %x\\n\", msg.EnvelopeHash)\n\t\treturn\n\t}\n\n//这是一个示例代码；如果不想保存自己的消息，请取消注释。\n//如果whisper.ispubkeyequal（msg.src，\u0026asymkey.publickey）\n//fmt.printf（“\\n%s\u003c%x\u003e：我收到的消息，未保存：“%s''\\n”，时间戳，地址，名称）\n//返回\n//}\n\n\tfullpath := filepath.Join(dir, name)\n\terr := ioutil.WriteFile(fullpath, env.Data, 0644)\n\tif err != nil {\n\t\tfmt.Printf(\"\\n%s {%x}: message received but not saved: %s\\n\", timestamp, address, err)\n\t} else if show {\n\t\tfmt.Printf(\"\\n%s {%x}: message received and saved as ''%s'' (%d bytes)\\n\", timestamp, address, name, len(env.Data))\n\t}\n}\n\nfunc requestExpiredMessagesLoop() {\n\tvar key, peerID, bloom []byte\n\tvar timeLow, timeUpp uint32\n\tvar t string\n\tvar xt whisper.TopicType\n\n\tkeyID, err := shh.AddSymKeyFromPassword(msPassword)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to create symmetric key for mail request: %s\", err)\n\t}\n\tkey, err = shh.GetSymKey(keyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to save symmetric key for mail request: %s\", err)\n\t}\n\tpeerID = extractIDFromEnode(*argEnode)\n\tshh.AllowP2PMessagesFromPeer(peerID)\n\n\tfor {\n\t\ttimeLow = scanUint(\"Please enter the lower limit of the time range (unix timestamp): \")\n\t\ttimeUpp = scanUint(\"Please enter the upper limit of the time range (unix timestamp): \")\n\t\tt = scanLine(\"Enter the topic (hex). Press enter to request all messages, regardless of the topic: \")\n\t\tif len(t) == whisper.TopicLength*2 {\n\t\t\tx, err := hex.DecodeString(t)\n\t\t\tif err != nil {\n\t\t\t\tfmt.Printf(\"Failed to parse the topic: %s \\n\", err)\n\t\t\t\tcontinue\n\t\t\t}\n\t\t\txt = whisper.BytesToTopic(x)\n\t\t\tbloom = whisper.TopicToBloom(xt)\n\t\t\tobfuscateBloom(bloom)\n\t\t} else if len(t) == 0 {\n\t\t\tbloom = whisper.MakeFullNodeBloom()\n\t\t} else {\n\t\t\tfmt.Println(\"Error: topic is invalid, request aborted\")\n\t\t\tcontinue\n\t\t}\n\n\t\tif timeUpp == 0 {\n\t\t\ttimeUpp = 0xFFFFFFFF\n\t\t}\n\n\t\tdata := make([]byte, 8, 8+whisper.BloomFilterSize)\n\t\tbinary.BigEndian.PutUint32(data, timeLow)\n\t\tbinary.BigEndian.PutUint32(data[4:], timeUpp)\n\t\tdata = append(data, bloom...)\n\n\t\tvar params whisper.MessageParams\n\t\tparams.PoW = *argServerPoW\n\t\tparams.Payload = data\n\t\tparams.KeySym = key\n\t\tparams.Src = asymKey\n\t\tparams.WorkTime = 5\n\n\t\tmsg, err := whisper.NewSentMessage(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t\t}\n\t\tenv, err := msg.Wrap(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Wrap failed: %s\", err)\n\t\t}\n\n\t\terr = shh.RequestHistoricMessages(peerID, env)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to send P2P message: %s\", err)\n\t\t}\n\n\t\ttime.Sleep(time.Second * 5)\n\t}\n}\n\nfunc extractIDFromEnode(s string) []byte {\n\tn, err := discover.ParseNode(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to parse enode: %s\", err)\n\t}\n\treturn n.ID[:]\n}\n\n//模糊布卢姆增加16个随机位的布卢姆\n//筛选，以便混淆包含的主题。\n//它在每个会话中都具有确定性。\n//尽管有额外的位，它将平均匹配\n//比完整节点的Bloom过滤器少32000倍的消息。\nfunc obfuscateBloom(bloom []byte) {\n\tconst half = entropySize / 2\n\tfor i := 0; i \u003c half; i++ {\n\t\tx := int(entropy[i])\n\t\tif entropy[half+i] \u003c 128 {\n\t\t\tx += 256\n\t\t}\n\nbloom[x/8] = 1 \u003c\u003c uint(x%8) //设置位号x\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":116,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/erigontech/erigon"},"file":{"path":"cmd/evm/internal/t8ntool/transition.go","url":"/github.com/erigontech/erigon/-/blob/cmd/evm/internal/t8ntool/transition.go","content":"// Copyright 2020 The go-ethereum Authors\n// (original work)\n// Copyright 2024 The Erigon Authors\n// (modifications)\n// This file is part of Erigon.\n//\n// Erigon is free software: you can redistribute it and/or modify\n// it under the terms of the GNU Lesser General Public License as published by\n// the Free Software Foundation, either version 3 of the License, or\n// (at your option) any later version.\n//\n// Erigon is distributed in the hope that it will be useful,\n// but WITHOUT ANY WARRANTY; without even the implied warranty of\n// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n// GNU Lesser General Public License for more details.\n//\n// You should have received a copy of the GNU Lesser General Public License\n// along with Erigon. If not, see \u003chttp://www.gnu.org/licenses/\u003e.\n\npackage t8ntool\n\nimport (\n\t\"context\"\n\t\"crypto/ecdsa\"\n\t\"encoding/json\"\n\t\"errors\"\n\t\"fmt\"\n\t\"math/big\"\n\t\"os\"\n\t\"path\"\n\t\"path/filepath\"\n\n\t\"github.com/holiman/uint256\"\n\t\"github.com/urfave/cli/v2\"\n\n\t\"github.com/erigontech/erigon/common\"\n\t\"github.com/erigontech/erigon/common/crypto\"\n\t\"github.com/erigontech/erigon/common/hexutil\"\n\t\"github.com/erigontech/erigon/common/length\"\n\t\"github.com/erigontech/erigon/common/log/v3\"\n\t\"github.com/erigontech/erigon/common/math\"\n\t\"github.com/erigontech/erigon/core\"\n\t\"github.com/erigontech/erigon/core/state\"\n\t\"github.com/erigontech/erigon/core/tracing\"\n\t\"github.com/erigontech/erigon/core/vm\"\n\t\"github.com/erigontech/erigon/core/vm/evmtypes\"\n\t\"github.com/erigontech/erigon/db/datadir\"\n\t\"github.com/erigontech/erigon/db/kv\"\n\t\"github.com/erigontech/erigon/db/kv/rawdbv3\"\n\t\"github.com/erigontech/erigon/db/kv/temporal/temporaltest\"\n\tdbstate \"github.com/erigontech/erigon/db/state\"\n\t\"github.com/erigontech/erigon/eth/consensuschain\"\n\ttrace_logger \"github.com/erigontech/erigon/eth/tracers/logger\"\n\t\"github.com/erigontech/erigon/execution/chain\"\n\t\"github.com/erigontech/erigon/execution/consensus/ethash\"\n\t\"github.com/erigontech/erigon/execution/consensus/merge\"\n\t\"github.com/erigontech/erigon/execution/rlp\"\n\t\"github.com/erigontech/erigon/execution/tests/testutil\"\n\t\"github.com/erigontech/erigon/execution/types\"\n\t\"github.com/erigontech/erigon/rpc/ethapi\"\n)\n\nconst (\n\tErrorEVM = 2\n\tErrorVMConfig = 3\n\tErrorMissingBlockhash = 4\n\n\tErrorJson = 10\n\tErrorIO = 11\n\n\tstdinSelector = \"stdin\"\n)\n\ntype NumberedError struct {\n\terrorCode int\n\terr error\n}\n\nfunc NewError(errorCode int, err error) *NumberedError {\n\treturn \u0026NumberedError{errorCode, err}\n}\n\nfunc (n *NumberedError) Error() string {\n\treturn fmt.Sprintf(\"ERROR(%d): %v\", n.errorCode, n.err.Error())\n}\n\nfunc (n *NumberedError) ExitCode() int {\n\treturn n.errorCode\n}\n\n// compile-time conformance test\nvar (\n\t_ cli.ExitCoder = (*NumberedError)(nil)\n)\n\ntype input struct {\n\tAlloc types.GenesisAlloc `json:\"alloc,omitempty\"`\n\tEnv *stEnv `json:\"env,omitempty\"`\n\tTxs []*txWithKey `json:\"txs,omitempty\"`\n}\n\nfunc Main(ctx *cli.Context) error {\n\tlog.Root().SetHandler(log.LvlFilterHandler(log.LvlInfo, log.StderrHandler))\n\tvar (\n\t\terr error\n\t\tbaseDir = \"\"\n\t)\n\tvar getTracer func(txIndex int, txHash common.Hash) (*tracing.Hooks, error)\n\n\t// If user specified a basedir, make sure it exists\n\tif ctx.IsSet(OutputBasedir.Name) {\n\t\tif base := ctx.String(OutputBasedir.Name); len(base) \u003e 0 {\n\t\t\terr2 := os.MkdirAll(base, 0755) // //rw-r--r--\n\t\t\tif err2 != nil {\n\t\t\t\treturn NewError(ErrorIO, fmt.Errorf(\"failed creating output basedir: %v\", err2))\n\t\t\t}\n\t\t\tbaseDir = base\n\t\t}\n\t}\n\tif ctx.Bool(TraceFlag.Name) {\n\t\t// Configure the EVM logger\n\t\tlogConfig := \u0026trace_logger.LogConfig{\n\t\t\tDisableStack: ctx.Bool(TraceDisableStackFlag.Name),\n\t\t\tDisableMemory: ctx.Bool(TraceDisableMemoryFlag.Name),\n\t\t\tDisableReturnData: ctx.Bool(TraceDisableReturnDataFlag.Name),\n\t\t\tDebug: true,\n\t\t}\n\t\tvar prevFile *os.File\n\t\t// This one closes the last file\n\t\tdefer func() {\n\t\t\tif prevFile != nil {\n\t\t\t\tprevFile.Close()\n\t\t\t}\n\t\t}()\n\t\tgetTracer = func(txIndex int, txHash common.Hash) (*tracing.Hooks, error) {\n\t\t\tif prevFile != nil {\n\t\t\t\tprevFile.Close()\n\t\t\t}\n\t\t\ttraceFile, err2 := os.Create(path.Join(baseDir, fmt.Sprintf(\"trace-%d-%v.jsonl\", txIndex, txHash.String())))\n\t\t\tif err2 != nil {\n\t\t\t\treturn nil, NewError(ErrorIO, fmt.Errorf(\"failed creating trace-file: %v\", err2))\n\t\t\t}\n\t\t\tprevFile = traceFile\n\t\t\treturn trace_logger.NewJSONLogger(logConfig, traceFile).Tracer().Hooks, nil\n\t\t}\n\t} else {\n\t\tgetTracer = func(txIndex int, txHash common.Hash) (tracer *tracing.Hooks, err error) {\n\t\t\treturn nil, nil\n\t\t}\n\t}\n\t// We need to load three things: alloc, env and transactions. May be either in\n\t// stdin input or in files.\n\t// Check if anything needs to be read from stdin\n\tvar (\n\t\tprestate Prestate\n\t\ttxs types.Transactions // txs to apply\n\t\tallocStr = ctx.String(InputAllocFlag.Name)\n\n\t\tenvStr = ctx.String(InputEnvFlag.Name)\n\t\ttxStr = ctx.String(InputTxsFlag.Name)\n\t\tinputData = \u0026input{}\n\t)\n\t// Figure out the prestate alloc\n\tif allocStr == stdinSelector || envStr == stdinSelector || txStr == stdinSelector {\n\t\tdecoder := json.NewDecoder(os.Stdin)\n\t\tdecoder.Decode(inputData) //nolint:errcheck\n\t}\n\tif allocStr != stdinSelector {\n\t\tinFile, err1 := os.Open(allocStr)\n\t\tif err1 != nil {\n\t\t\treturn NewError(ErrorIO, fmt.Errorf(\"failed reading alloc file: %v\", err1))\n\t\t}\n\t\tdefer inFile.Close()\n\t\tdecoder := json.NewDecoder(inFile)\n\t\tif err = decoder.Decode(\u0026inputData.Alloc); err != nil {\n\t\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed unmarshaling alloc-file: %v\", err))\n\t\t}\n\t}\n\n\tprestate.Pre = inputData.Alloc\n\n\t// Set the block environment\n\tif envStr != stdinSelector {\n\t\tinFile, err1 := os.Open(envStr)\n\t\tif err1 != nil {\n\t\t\treturn NewError(ErrorIO, fmt.Errorf(\"failed reading env file: %v\", err1))\n\t\t}\n\t\tdefer inFile.Close()\n\t\tdecoder := json.NewDecoder(inFile)\n\t\tvar env stEnv\n\t\tif err = decoder.Decode(\u0026env); err != nil {\n\t\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed unmarshaling env-file: %v\", err))\n\t\t}\n\t\tinputData.Env = \u0026env\n\t}\n\tprestate.Env = *inputData.Env\n\n\tvmConfig := vm.Config{\n\t\tTracer: nil,\n\t\tStatelessExec: true,\n\t}\n\t// Construct the chainconfig\n\tvar chainConfig *chain.Config\n\tif cConf, extraEips, err1 := testutil.GetChainConfig(ctx.String(ForknameFlag.Name)); err1 != nil {\n\t\treturn NewError(ErrorVMConfig, fmt.Errorf(\"failed constructing chain configuration: %v\", err1))\n\t} else {\n\t\tchainConfig = cConf\n\t\tvmConfig.ExtraEips = extraEips\n\t}\n\t// Set the chain id\n\tchainConfig.ChainID = big.NewInt(ctx.Int64(ChainIDFlag.Name))\n\n\tvar txsWithKeys []*txWithKey\n\tif txStr != stdinSelector {\n\t\tinFile, err1 := os.Open(txStr)\n\t\tif err1 != nil {\n\t\t\treturn NewError(ErrorIO, fmt.Errorf(\"failed reading txs file: %v\", err1))\n\t\t}\n\t\tdefer inFile.Close()\n\t\tdecoder := json.NewDecoder(inFile)\n\t\tif err = decoder.Decode(\u0026txsWithKeys); err != nil {\n\t\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed unmarshaling txs-file: %v\", err))\n\t\t}\n\t} else {\n\t\ttxsWithKeys = inputData.Txs\n\t}\n\t// We may have to sign the transactions.\n\tsigner := types.MakeSigner(chainConfig, prestate.Env.Number, prestate.Env.Timestamp)\n\n\tif txs, err = signUnsignedTransactions(txsWithKeys, *signer); err != nil {\n\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed signing transactions: %v\", err))\n\t}\n\n\teip1559 := chainConfig.IsLondon(prestate.Env.Number)\n\t// Sanity check, to not `panic` in state_transition\n\tif eip1559 {\n\t\tif prestate.Env.BaseFee == nil {\n\t\t\treturn NewError(ErrorVMConfig, errors.New(\"EIP-1559 config but missing ''currentBaseFee'' in env section\"))\n\t\t}\n\t} else {\n\t\tprestate.Env.Random = nil\n\t}\n\n\tif chainConfig.IsShanghai(prestate.Env.Timestamp) \u0026\u0026 prestate.Env.Withdrawals == nil {\n\t\treturn NewError(ErrorVMConfig, errors.New(\"shanghai config but missing ''withdrawals'' in env section\"))\n\t}\n\n\tisMerged := chainConfig.TerminalTotalDifficulty != nil \u0026\u0026 chainConfig.TerminalTotalDifficulty.BitLen() == 0\n\tenv := prestate.Env\n\tif isMerged {\n\t\t// post-merge:\n\t\t// - random must be supplied\n\t\t// - difficulty must be zero\n\t\tswitch {\n\t\tcase env.Random == nil:\n\t\t\treturn NewError(ErrorVMConfig, errors.New(\"post-merge requires currentRandom to be defined in env\"))\n\t\tcase env.Difficulty != nil \u0026\u0026 env.Difficulty.BitLen() != 0:\n\t\t\treturn NewError(ErrorVMConfig, errors.New(\"post-merge difficulty must be zero (or omitted) in env\"))\n\t\t}\n\t\tprestate.Env.Difficulty = nil\n\t} else if env.Difficulty == nil {\n\t\t// If difficulty was not provided by caller, we need to calculate it.\n\t\tswitch {\n\t\tcase env.ParentDifficulty == nil:\n\t\t\treturn NewError(ErrorVMConfig, errors.New(\"currentDifficulty was not provided, and cannot be calculated due to missing parentDifficulty\"))\n\t\tcase env.Number == 0:\n\t\t\treturn NewError(ErrorVMConfig, errors.New(\"currentDifficulty needs to be provided for block number 0\"))\n\t\tcase env.Timestamp \u003c= env.ParentTimestamp:\n\t\t\treturn NewError(ErrorVMConfig, fmt.Errorf(\"currentDifficulty cannot be calculated -- currentTime (%d) needs to be after parent time (%d)\",\n\t\t\t\tenv.Timestamp, env.ParentTimestamp))\n\t\t}\n\t\tprestate.Env.Difficulty = calcDifficulty(chainConfig, env.Number, env.Timestamp,\n\t\t\tenv.ParentTimestamp, env.ParentDifficulty, env.ParentUncleHash)\n\t}\n\n\t// manufacture block from above inputs\n\theader := NewHeader(prestate.Env)\n\n\tvar ommerHeaders = make([]*types.Header, len(prestate.Env.Ommers))\n\theader.Number.Add(header.Number, big.NewInt(int64(len(prestate.Env.Ommers))))\n\tfor i, ommer := range prestate.Env.Ommers {\n\t\tvar ommerN big.Int\n\t\tommerN.SetUint64(header.Number.Uint64() - ommer.Delta)\n\t\tommerHeaders[i] = \u0026types.Header{Coinbase: ommer.Address, Number: \u0026ommerN}\n\t}\n\tblock := types.NewBlock(header, txs, ommerHeaders, nil /* receipts */, prestate.Env.Withdrawals)\n\n\tgetHash := func(num uint64) (common.Hash, error) {\n\t\tif prestate.Env.BlockHashes == nil {\n\t\t\treturn common.Hash{}, fmt.Errorf(\"getHash(%d) invoked, no blockhashes provided\", num)\n\t\t}\n\t\th, ok := prestate.Env.BlockHashes[math.HexOrDecimal64(num)]\n\t\tif !ok {\n\t\t\treturn common.Hash{}, fmt.Errorf(\"getHash(%d) invoked, blockhash for that block not provided\", num)\n\t\t}\n\t\treturn h, nil\n\t}\n\n\tdb := temporaltest.NewTestDB(nil, datadir.New(\"\"))\n\tdefer db.Close()\n\n\ttx, err := db.BeginTemporalRw(context.Background())\n\tif err != nil {\n\t\treturn err\n\t}\n\tdefer tx.Rollback()\n\n\tsd, err := dbstate.NewSharedDomains(tx, log.New())\n\tif err != nil {\n\t\treturn err\n\t}\n\tdefer sd.Close()\n\n\tblockNum, txNum := uint64(0), uint64(0)\n\tsd.SetTxNum(txNum)\n\tsd.SetBlockNum(blockNum)\n\treader, writer := MakePreState((\u0026evmtypes.BlockContext{}).Rules(chainConfig), tx, sd, prestate.Pre, blockNum, txNum)\n\tblockNum, txNum = uint64(1), uint64(2)\n\tsd.SetTxNum(txNum)\n\tsd.SetBlockNum(blockNum)\n\n\t// Merge engine can be used for pre-merge blocks as well, as it\n\t// redirects to the ethash engine based on the block number\n\tengine := merge.New(\u0026ethash.FakeEthash{})\n\n\tt8logger := log.New(\"t8ntool\")\n\tchainReader := consensuschain.NewReader(chainConfig, tx, nil, t8logger)\n\tresult, err := core.ExecuteBlockEphemerally(chainConfig, \u0026vmConfig, getHash, engine, block, reader, writer, chainReader, getTracer, t8logger)\n\n\tif err != nil {\n\t\treturn fmt.Errorf(\"error on EBE: %w\", err)\n\t}\n\n\t// state root calculation\n\troot, err := CalculateStateRoot(tx, blockNum, txNum)\n\tif err != nil {\n\t\treturn err\n\t}\n\tresult.StateRoot = *root\n\n\t// Dump the execution result\n\tbody, _ := rlp.EncodeToBytes(txs)\n\tcollector := make(Alloc)\n\n\tdumper := state.NewDumper(tx, rawdbv3.TxNums, prestate.Env.Number)\n\tdumper.DumpToCollector(collector, false, false, common.Address{}, 0)\n\treturn dispatchOutput(ctx, baseDir, result, collector, body)\n}\n\n// txWithKey is a helper-struct, to allow us to use the types.Transaction along with\n// a `secretKey`-field, for input\ntype txWithKey struct {\n\tkey *ecdsa.PrivateKey\n\ttx types.Transaction\n}\n\nfunc (t *txWithKey) UnmarshalJSON(input []byte) error {\n\t// Read the secretKey, if present\n\ttype sKey struct {\n\t\tKey *common.Hash `json:\"secretKey\"`\n\t}\n\tvar key sKey\n\tif err := json.Unmarshal(input, \u0026key); err != nil {\n\t\treturn err\n\t}\n\tif key.Key != nil {\n\t\tk := key.Key.Hex()[2:]\n\t\tif ecdsaKey, err := crypto.HexToECDSA(k); err == nil {\n\t\t\tt.key = ecdsaKey\n\t\t} else {\n\t\t\treturn err\n\t\t}\n\t}\n\n\t// Now, read the transaction itself\n\tvar txJson ethapi.RPCTransaction\n\n\tif err := json.Unmarshal(input, \u0026txJson); err != nil {\n\t\treturn err\n\t}\n\n\t// assemble transaction\n\ttx, err := getTransaction(txJson)\n\tif err != nil {\n\t\treturn err\n\t}\n\tt.tx = tx\n\treturn nil\n}\n\nfunc getTransaction(txJson ethapi.RPCTransaction) (types.Transaction, error) {\n\tgasPrice, value := uint256.NewInt(0), uint256.NewInt(0)\n\tvar overflow bool\n\tvar chainId *uint256.Int\n\n\tif txJson.Value != nil {\n\t\tvalue, overflow = uint256.FromBig(txJson.Value.ToInt())\n\t\tif overflow {\n\t\t\treturn nil, errors.New(\"value field caused an overflow (uint256)\")\n\t\t}\n\t}\n\n\tif txJson.GasPrice != nil {\n\t\tgasPrice, overflow = uint256.FromBig(txJson.GasPrice.ToInt())\n\t\tif overflow {\n\t\t\treturn nil, errors.New(\"gasPrice field caused an overflow (uint256)\")\n\t\t}\n\t}\n\n\tif txJson.ChainID != nil {\n\t\tchainId, overflow = uint256.FromBig(txJson.ChainID.ToInt())\n\t\tif overflow {\n\t\t\treturn nil, errors.New(\"chainId field caused an overflow (uint256)\")\n\t\t}\n\t}\n\n\tcommonTx := types.CommonTx{\n\t\tNonce: uint64(txJson.Nonce),\n\t\tTo: txJson.To,\n\t\tValue: value,\n\t\tGasLimit: uint64(txJson.Gas),\n\t\tData: txJson.Input,\n\t}\n\n\tcommonTx.V.SetFromBig(txJson.V.ToInt())\n\tcommonTx.R.SetFromBig(txJson.R.ToInt())\n\tcommonTx.S.SetFromBig(txJson.S.ToInt())\n\tif txJson.Type == types.LegacyTxType || txJson.Type == types.AccessListTxType {\n\t\tif txJson.Type == types.LegacyTxType {\n\t\t\treturn \u0026types.LegacyTx{\n\t\t\t\tCommonTx: types.CommonTx{\n\t\t\t\t\tNonce: uint64(txJson.Nonce),\n\t\t\t\t\tTo: txJson.To,\n\t\t\t\t\tValue: value,\n\t\t\t\t\tGasLimit: uint64(txJson.Gas),\n\t\t\t\t\tData: txJson.Input,\n\t\t\t\t},\n\t\t\t\tGasPrice: gasPrice,\n\t\t\t}, nil\n\t\t}\n\n\t\treturn \u0026types.AccessListTx{\n\t\t\tLegacyTx: types.LegacyTx{\n\t\t\t\tCommonTx: types.CommonTx{\n\t\t\t\t\tNonce: uint64(txJson.Nonce),\n\t\t\t\t\tTo: txJson.To,\n\t\t\t\t\tValue: value,\n\t\t\t\t\tGasLimit: uint64(txJson.Gas),\n\t\t\t\t\tData: txJson.Input,\n\t\t\t\t},\n\t\t\t\tGasPrice: gasPrice,\n\t\t\t},\n\t\t\tChainID: chainId,\n\t\t\tAccessList: *txJson.Accesses,\n\t\t}, nil\n\t} else if txJson.Type == types.DynamicFeeTxType || txJson.Type == types.SetCodeTxType {\n\t\tvar tipCap *uint256.Int\n\t\tvar feeCap *uint256.Int\n\t\tif txJson.MaxPriorityFeePerGas != nil {\n\t\t\ttipCap, overflow = uint256.FromBig(txJson.MaxPriorityFeePerGas.ToInt())\n\t\t\tif overflow {\n\t\t\t\treturn nil, errors.New(\"maxPriorityFeePerGas field caused an overflow (uint256)\")\n\t\t\t}\n\t\t}\n\n\t\tif txJson.MaxFeePerGas != nil {\n\t\t\tfeeCap, overflow = uint256.FromBig(txJson.MaxFeePerGas.ToInt())\n\t\t\tif overflow {\n\t\t\t\treturn nil, errors.New(\"maxFeePerGas field caused an overflow (uint256)\")\n\t\t\t}\n\t\t}\n\n\t\tif txJson.Type == types.DynamicFeeTxType {\n\t\t\treturn \u0026types.DynamicFeeTransaction{\n\t\t\t\tCommonTx: types.CommonTx{\n\t\t\t\t\tNonce: uint64(txJson.Nonce),\n\t\t\t\t\tTo: txJson.To,\n\t\t\t\t\tValue: value,\n\t\t\t\t\tGasLimit: uint64(txJson.Gas),\n\t\t\t\t\tData: txJson.Input,\n\t\t\t\t},\n\t\t\t\tChainID: chainId,\n\t\t\t\tTipCap: tipCap,\n\t\t\t\tFeeCap: feeCap,\n\t\t\t\tAccessList: *txJson.Accesses,\n\t\t\t}, nil\n\t\t}\n\n\t\tauths := make([]types.Authorization, 0)\n\t\tfor _, auth := range *txJson.Authorizations {\n\t\t\ta, err := auth.ToAuthorization()\n\t\t\tif err != nil {\n\t\t\t\treturn nil, err\n\t\t\t}\n\t\t\tauths = append(auths, a)\n\t\t}\n\n\t\treturn \u0026types.SetCodeTransaction{\n\t\t\t// it''s ok to copy here - because it''s constructor of object - no parallel access yet\n\t\t\tDynamicFeeTransaction: types.DynamicFeeTransaction{\n\t\t\t\tCommonTx: types.CommonTx{\n\t\t\t\t\tNonce: uint64(txJson.Nonce),\n\t\t\t\t\tTo: txJson.To,\n\t\t\t\t\tValue: value,\n\t\t\t\t\tGasLimit: uint64(txJson.Gas),\n\t\t\t\t\tData: txJson.Input,\n\t\t\t\t},\n\t\t\t\tChainID: chainId,\n\t\t\t\tTipCap: tipCap,\n\t\t\t\tFeeCap: feeCap,\n\t\t\t\tAccessList: *txJson.Accesses,\n\t\t\t},\n\t\t\tAuthorizations: auths,\n\t\t}, nil\n\t} else {\n\t\treturn nil, nil\n\t}\n}\n\n// signUnsignedTransactions converts the input txs to canonical transactions.\n//\n// The transactions can have two forms, either\n// 1. unsigned or\n// 2. signed\n//\n// For (1), r, s, v, need so be zero, and the `secretKey` needs to be set.\n// If so, we sign it here and now, with the given `secretKey`\n// If the condition above is not met, then it''s considered a signed transaction.\n//\n// To manage this, we read the transactions twice, first trying to read the secretKeys,\n// and secondly to read them with the standard txn json format\nfunc signUnsignedTransactions(txs []*txWithKey, signer types.Signer) (types.Transactions, error) {\n\tvar signedTxs []types.Transaction\n\tfor i, txWithKey := range txs {\n\t\ttx := txWithKey.tx\n\t\tkey := txWithKey.key\n\t\tv, r, s := tx.RawSignatureValues()\n\t\tif key != nil \u0026\u0026 v.IsZero() \u0026\u0026 r.IsZero() \u0026\u0026 s.IsZero() {\n\t\t\t// This transaction needs to be signed\n\t\t\tsigned, err := types.SignTx(tx, signer, key)\n\t\t\tif err != nil {\n\t\t\t\treturn nil, NewError(ErrorJson, fmt.Errorf(\"tx %d: failed to sign tx: %v\", i, err))\n\t\t\t}\n\t\t\tsignedTxs = append(signedTxs, signed)\n\t\t} else {\n\t\t\t// Already signed\n\t\t\tsignedTxs = append(signedTxs, tx)\n\t\t}\n\t}\n\treturn signedTxs, nil\n}\n\ntype Alloc map[common.Address]types.GenesisAccount\n\nfunc (g Alloc) OnRoot(common.Hash) {}\n\nfunc (g Alloc) OnAccount(addr common.Address, dumpAccount state.DumpAccount) {\n\tbalance, _ := new(big.Int).SetString(dumpAccount.Balance, 10)\n\tvar storage map[common.Hash]common.Hash\n\tif dumpAccount.Storage != nil {\n\t\tstorage = make(map[common.Hash]common.Hash)\n\t\tfor k, v := range dumpAccount.Storage {\n\t\t\tstorage[common.HexToHash(k)] = common.HexToHash(v)\n\t\t}\n\t}\n\tgenesisAccount := types.GenesisAccount{\n\t\tCode: dumpAccount.Code,\n\t\tStorage: storage,\n\t\tBalance: balance,\n\t\tNonce: dumpAccount.Nonce,\n\t}\n\tg[addr] = genesisAccount\n}\n\n// saveFile marshalls the object to the given file\nfunc saveFile(baseDir, filename string, data interface{}) error {\n\tb, err := json.MarshalIndent(data, \"\", \" \")\n\tif err != nil {\n\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed marshalling output: %v\", err))\n\t}\n\tlocation := filepath.Join(baseDir, filename)\n\tif err = os.WriteFile(location, b, 0644); err != nil { //nolint:gosec\n\t\treturn NewError(ErrorIO, fmt.Errorf(\"failed writing output: %v\", err))\n\t}\n\tlog.Info(\"Wrote file\", \"file\", location)\n\treturn nil\n}\n\n// dispatchOutput writes the output data to either stderr or stdout, or to the specified\n// files\nfunc dispatchOutput(ctx *cli.Context, baseDir string, result *core.EphemeralExecResult, alloc Alloc, body hexutil.Bytes) error {\n\tstdOutObject := make(map[string]interface{})\n\tstdErrObject := make(map[string]interface{})\n\tdispatch := func(baseDir, fName, name string, obj interface{}) error {\n\t\tswitch fName {\n\t\tcase \"stdout\":\n\t\t\tstdOutObject[name] = obj\n\t\tcase \"stderr\":\n\t\t\tstdErrObject[name] = obj\n\t\tcase \"\":\n\t\t\t// don''t save\n\t\tdefault: // save to file\n\t\t\tif err := saveFile(baseDir, fName, obj); err != nil {\n\t\t\t\treturn err\n\t\t\t}\n\t\t}\n\t\treturn nil\n\t}\n\tif err := dispatch(baseDir, ctx.String(OutputAllocFlag.Name), \"alloc\", alloc); err != nil {\n\t\treturn err\n\t}\n\tif err := dispatch(baseDir, ctx.String(OutputResultFlag.Name), \"result\", result); err != nil {\n\t\treturn err\n\t}\n\tif err := dispatch(baseDir, ctx.String(OutputBodyFlag.Name), \"body\", body); err != nil {\n\t\treturn err\n\t}\n\tif len(stdOutObject) \u003e 0 {\n\t\tb, err := json.MarshalIndent(stdOutObject, \"\", \" \")\n\t\tif err != nil {\n\t\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed marshalling output: %v\", err))\n\t\t}\n\t\tos.Stdout.Write(b)\n\t}\n\tif len(stdErrObject) \u003e 0 {\n\t\tb, err := json.MarshalIndent(stdErrObject, \"\", \" \")\n\t\tif err != nil {\n\t\t\treturn NewError(ErrorJson, fmt.Errorf(\"failed marshalling output: %v\", err))\n\t\t}\n\t\tos.Stderr.Write(b)\n\t}\n\treturn nil\n}\n\nfunc NewHeader(env stEnv) *types.Header {\n\tvar header types.Header\n\theader.Coinbase = env.Coinbase\n\theader.Difficulty = env.Difficulty\n\theader.GasLimit = env.GasLimit\n\theader.Number = new(big.Int).SetUint64(env.Number)\n\theader.Time = env.Timestamp\n\theader.BaseFee = env.BaseFee\n\theader.MixDigest = env.MixDigest\n\n\theader.UncleHash = env.UncleHash\n\theader.WithdrawalsHash = env.WithdrawalsHash\n\theader.RequestsHash = env.RequestsHash\n\n\treturn \u0026header\n}\n\nfunc CalculateStateRoot(tx kv.TemporalRwTx, blockNum uint64, txNum uint64) (*common.Hash, error) {\n\t// Generate hashed state\n\tc, err := tx.RwCursor(kv.PlainState)\n\tif err != nil {\n\t\treturn nil, err\n\t}\n\tdefer c.Close()\n\th := common.NewHasher()\n\tdefer common.ReturnHasherToPool(h)\n\tdomains, err := dbstate.NewSharedDomains(tx, log.New())\n\tif err != nil {\n\t\treturn nil, fmt.Errorf(\"NewSharedDomains: %w\", err)\n\t}\n\tdefer domains.Close()\n\n\tfor k, v, err := c.First(); k != nil; k, v, err = c.Next() {\n\t\tif err != nil {\n\t\t\treturn nil, fmt.Errorf(\"interate over plain state: %w\", err)\n\t\t}\n\t\tvar newK []byte\n\t\tif len(k) == length.Addr {\n\t\t\tnewK = make([]byte, length.Hash)\n\t\t} else {\n\t\t\tnewK = make([]byte, length.Hash*2+length.Incarnation)\n\t\t}\n\t\th.Sha.Reset()\n\t\t//nolint:errcheck\n\t\th.Sha.Write(k[:length.Addr])\n\t\t//nolint:errcheck\n\t\th.Sha.Read(newK[:length.Hash])\n\t\tif len(k) \u003e length.Addr {\n\t\t\tcopy(newK[length.Hash:], k[length.Addr:length.Addr+length.Incarnation])\n\t\t\th.Sha.Reset()\n\t\t\t//nolint:errcheck\n\t\t\th.Sha.Write(k[length.Addr+length.Incarnation:])\n\t\t\t//nolint:errcheck\n\t\t\th.Sha.Read(newK[length.Hash+length.Incarnation:])\n\t\t\tif err = tx.Put(kv.HashedStorageDeprecated, newK, common.CopyBytes(v)); err != nil {\n\t\t\t\treturn nil, fmt.Errorf(\"insert hashed key: %w\", err)\n\t\t\t}\n\t\t} else {\n\t\t\tif err = tx.Put(kv.HashedAccountsDeprecated, newK, common.CopyBytes(v)); err != nil {\n\t\t\t\treturn nil, fmt.Errorf(\"insert hashed key: %w\", err)\n\t\t\t}\n\t\t}\n\t}\n\tc.Close()\n\troot, err := domains.ComputeCommitment(context.Background(), tx, true, blockNum, txNum, \"\", nil)\n\tif err != nil {\n\t\treturn nil, err\n\t}\n\thashRoot := common.Hash{}\n\thashRoot.SetBytes(root)\n\n\treturn \u0026hashRoot, nil\n}\n"},"lineMatches":[{"preview":"func Main(ctx *cli.Context) error {","lineNumber":101,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/cilium/hubble"},"file":{"path":"vendor/github.com/google/gnostic-models/extensions/extensions.go","url":"/github.com/cilium/hubble/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go","content":"// Copyright 2017 Google LLC. All Rights Reserved.\n//\n// Licensed under the Apache License, Version 2.0 (the \"License\");\n// you may not use this file except in compliance with the License.\n// You may obtain a copy of the License at\n//\n// http://www.apache.org/licenses/LICENSE-2.0\n//\n// Unless required by applicable law or agreed to in writing, software\n// distributed under the License is distributed on an \"AS IS\" BASIS,\n// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n// See the License for the specific language governing permissions and\n// limitations under the License.\n\npackage gnostic_extension_v1\n\nimport (\n\t\"io/ioutil\"\n\t\"log\"\n\t\"os\"\n\n\t\"google.golang.org/protobuf/proto\"\n\t\"google.golang.org/protobuf/types/known/anypb\"\n)\n\ntype extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\n\n// Main implements the main program of an extension handler.\nfunc Main(handler extensionHandler) {\n\t// unpack the request\n\tdata, err := ioutil.ReadAll(os.Stdin)\n\tif err != nil {\n\t\tlog.Println(\"File error:\", err.Error())\n\t\tos.Exit(1)\n\t}\n\tif len(data) == 0 {\n\t\tlog.Println(\"No input data.\")\n\t\tos.Exit(1)\n\t}\n\trequest := \u0026ExtensionHandlerRequest{}\n\terr = proto.Unmarshal(data, request)\n\tif err != nil {\n\t\tlog.Println(\"Input error:\", err.Error())\n\t\tos.Exit(1)\n\t}\n\t// call the handler\n\thandled, output, err := handler(request.Wrapper.ExtensionName, request.Wrapper.Yaml)\n\t// respond with the output of the handler\n\tresponse := \u0026ExtensionHandlerResponse{\n\t\tHandled: false, // default assumption\n\t\tErrors: make([]string, 0),\n\t}\n\tif err != nil {\n\t\tresponse.Errors = append(response.Errors, err.Error())\n\t} else if handled {\n\t\tresponse.Handled = true\n\t\tresponse.Value, err = anypb.New(output)\n\t\tif err != nil {\n\t\t\tresponse.Errors = append(response.Errors, err.Error())\n\t\t}\n\t}\n\tresponseBytes, _ := proto.Marshal(response)\n\tos.Stdout.Write(responseBytes)\n}\n"},"lineMatches":[{"preview":"func Main(handler extensionHandler) {","lineNumber":28,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/eclipse-che/che-operator"},"file":{"path":"vendor/github.com/google/gnostic-models/extensions/extensions.go","url":"/github.com/eclipse-che/che-operator/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go","content":"// Copyright 2017 Google LLC. All Rights Reserved.\n//\n// Licensed under the Apache License, Version 2.0 (the \"License\");\n// you may not use this file except in compliance with the License.\n// You may obtain a copy of the License at\n//\n// http://www.apache.org/licenses/LICENSE-2.0\n//\n// Unless required by applicable law or agreed to in writing, software\n// distributed under the License is distributed on an \"AS IS\" BASIS,\n// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n// See the License for the specific language governing permissions and\n// limitations under the License.\n\npackage gnostic_extension_v1\n\nimport (\n\t\"io/ioutil\"\n\t\"log\"\n\t\"os\"\n\n\t\"google.golang.org/protobuf/proto\"\n\t\"google.golang.org/protobuf/types/known/anypb\"\n)\n\ntype extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\n\n// Main implements the main program of an extension handler.\nfunc Main(handler extensionHandler) {\n\t// unpack the request\n\tdata, err := ioutil.ReadAll(os.Stdin)\n\tif err != nil {\n\t\tlog.Println(\"File error:\", err.Error())\n\t\tos.Exit(1)\n\t}\n\tif len(data) == 0 {\n\t\tlog.Println(\"No input data.\")\n\t\tos.Exit(1)\n\t}\n\trequest := \u0026ExtensionHandlerRequest{}\n\terr = proto.Unmarshal(data, request)\n\tif err != nil {\n\t\tlog.Println(\"Input error:\", err.Error())\n\t\tos.Exit(1)\n\t}\n\t// call the handler\n\thandled, output, err := handler(request.Wrapper.ExtensionName, request.Wrapper.Yaml)\n\t// respond with the output of the handler\n\tresponse := \u0026ExtensionHandlerResponse{\n\t\tHandled: false, // default assumption\n\t\tErrors: make([]string, 0),\n\t}\n\tif err != nil {\n\t\tresponse.Errors = append(response.Errors, err.Error())\n\t} else if handled {\n\t\tresponse.Handled = true\n\t\tresponse.Value, err = anypb.New(output)\n\t\tif err != nil {\n\t\t\tresponse.Errors = append(response.Errors, err.Error())\n\t\t}\n\t}\n\tresponseBytes, _ := proto.Marshal(response)\n\tos.Stdout.Write(responseBytes)\n}\n"},"lineMatches":[{"preview":"func Main(handler extensionHandler) {","lineNumber":28,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/wader/fq"},"file":{"path":"pkg/cli/cli.go","url":"/github.com/wader/fq/-/blob/pkg/cli/cli.go","content":"package cli\n\nimport (\n\t\"bufio\"\n\t\"context\"\n\t\"errors\"\n\t\"fmt\"\n\t\"io\"\n\t\"io/fs\"\n\t\"log\"\n\t\"os\"\n\t\"os/signal\"\n\t\"path/filepath\"\n\t\"runtime\"\n\n\t\"github.com/wader/fq/pkg/interp\"\n\t\"golang.org/x/term\"\n\n\t\"github.com/ergochat/readline\"\n)\n\nfunc maybeLogFile() {\n\t// used during dev to redirect log to file, useful when debugging repl etc\n\tif lf := os.Getenv(\"LOGFILE\"); lf != \"\" {\n\t\tif f, err := os.Create(lf); err == nil {\n\t\t\tlog.SetOutput(f)\n\t\t}\n\t}\n}\n\n// function implementing readline.AutoComplete interface\ntype autoCompleterFn func(line []rune, pos int) (newLine [][]rune, length int)\n\nfunc (a autoCompleterFn) Do(line []rune, pos int) (newLine [][]rune, length int) {\n\treturn a(line, pos)\n}\n\ntype stdOS struct {\n\trl *readline.Instance\n\thistoryFile string\n\tcloseChan chan struct{}\n\tinterruptChan chan struct{}\n\tcompleterFn interp.CompleteFn\n}\n\nfunc newStandardOS() *stdOS {\n\tcloseChan := make(chan struct{})\n\tinterruptChan := make(chan struct{}, 1)\n\n\t// this more or less converts a os signal chan to just a struct{} chan that\n\t// ignores signals if forwarding it would block, also this makes sure interp\n\t// does not know about os.\n\tgo func() {\n\t\tinterruptSignalChan := make(chan os.Signal, 1)\n\t\tsignal.Notify(interruptSignalChan, os.Interrupt)\n\t\tdefer func() {\n\t\t\tsignal.Stop(interruptSignalChan)\n\t\t\tclose(interruptSignalChan)\n\t\t\tclose(interruptChan)\n\t\t}()\n\n\t\tfor {\n\t\t\tselect {\n\t\t\tcase \u003c-interruptSignalChan:\n\t\t\t\t// ignore if interruptChan is full\n\t\t\t\tselect {\n\t\t\t\tcase interruptChan \u003c- struct{}{}:\n\t\t\t\tdefault:\n\t\t\t\t}\n\t\t\tcase \u003c-closeChan:\n\t\t\t\treturn\n\t\t\t}\n\t\t}\n\t}()\n\n\treturn \u0026stdOS{\n\t\tcloseChan: closeChan,\n\t\tinterruptChan: interruptChan,\n\t}\n}\n\nfunc (stdOS) Platform() interp.Platform {\n\treturn interp.Platform{\n\t\tOS: runtime.GOOS,\n\t\tArch: runtime.GOARCH,\n\t\tGoVersion: runtime.Version(),\n\t}\n}\n\ntype fdTerminal uintptr\n\nfunc (fd fdTerminal) Size() (int, int) {\n\tw, h, _ := term.GetSize(int(fd))\n\t// TODO: old version return 0 on no terminal\n\tw, h = max(0, w), max(0, h)\n\treturn w, h\n}\nfunc (fd fdTerminal) IsTerminal() bool {\n\treturn term.IsTerminal(int(fd))\n}\n\ntype stdinInput struct {\n\tfdTerminal\n\tfs.File\n}\n\nfunc (o *stdOS) Stdin() interp.Input {\n\treturn stdinInput{\n\t\tfdTerminal: fdTerminal(os.Stdin.Fd()),\n\t\tFile: interp.FileReader{\n\t\t\tR: os.Stdin,\n\t\t\tFileInfo: interp.FixedFileInfo{\n\t\t\t\tFName: \"stdin\",\n\t\t\t\tFMode: fs.ModeIrregular,\n\t\t\t},\n\t\t},\n\t}\n}\n\ntype stdoutOutput struct {\n\tfdTerminal\n\tos *stdOS\n}\n\nfunc (o stdoutOutput) Write(p []byte) (n int, err error) {\n\t// Let write go thru readline if it has been used. This to have ansi color emulation\n\t// on windows thru readlins:s stdout rewriter\n\t// TODO: check if tty instead? else only color when repl\n\tif o.os.rl != nil {\n\t\treturn o.os.rl.Write(p)\n\t}\n\treturn os.Stdout.Write(p)\n}\n\nfunc (o *stdOS) Stdout() interp.Output {\n\treturn stdoutOutput{fdTerminal: fdTerminal(os.Stdout.Fd()), os: o}\n}\n\ntype stderrOutput struct {\n\tfdTerminal\n}\n\nfunc (o stderrOutput) Write(p []byte) (n int, err error) { return os.Stderr.Write(p) }\n\nfunc (o *stdOS) Stderr() interp.Output { return stderrOutput{fdTerminal: fdTerminal(os.Stderr.Fd())} }\n\nfunc (o *stdOS) InterruptChan() chan struct{} { return o.interruptChan }\n\nfunc (*stdOS) Args() []string { return os.Args }\n\nfunc (*stdOS) Environ() []string { return os.Environ() }\n\nfunc (*stdOS) ConfigDir() (string, error) {\n\tconfigDir, err := os.UserConfigDir()\n\tif err != nil {\n\t\treturn \"\", err\n\t}\n\tfqDir := filepath.Join(configDir, \"fq\")\n\n\tif runtime.GOOS != \"darwin\" {\n\t\treturn fqDir, nil\n\t}\n\n\t// this is to support fallback to ~/.config on macOS/darwin\n\tif _, err := os.Stat(fqDir); err == nil {\n\t\treturn fqDir, nil\n\t}\n\n\thomeDir, err := os.UserHomeDir()\n\tif err != nil {\n\t\treturn \"\", err\n\t}\n\n\treturn filepath.Join(homeDir, \".config\", \"fq\"), nil\n}\n\ntype stdOSFS struct{}\n\nfunc (stdOSFS) Open(name string) (fs.File, error) { return os.Open(name) }\n\nfunc (*stdOS) FS() fs.FS { return stdOSFS{} }\n\nfunc (o *stdOS) Readline(opts interp.ReadlineOpts) (string, error) {\n\tif o.rl == nil {\n\t\tvar err error\n\n\t\tvar historyFile string\n\t\tcacheDir, err := os.UserCacheDir()\n\t\tif err != nil {\n\t\t\treturn \"\", err\n\t\t}\n\t\thistoryFile = filepath.Join(cacheDir, \"fq/history\")\n\t\t_ = os.MkdirAll(filepath.Dir(historyFile), 0700)\n\n\t\tcfg := \u0026readline.Config{\n\t\t\tHistoryFile: historyFile,\n\t\t\tHistorySearchFold: true,\n\t\t\tUndo: true,\n\t\t}\n\t\tcfg.AutoComplete = autoCompleterFn(func(line []rune, pos int) (newLine [][]rune, length int) {\n\t\t\tif o.completerFn == nil {\n\t\t\t\treturn nil, 0\n\t\t\t}\n\n\t\t\tnames, shared := o.completerFn(string(line), pos)\n\t\t\tvar runeNames [][]rune\n\t\t\tfor _, name := range names {\n\t\t\t\truneNames = append(runeNames, []rune(name[shared:]))\n\t\t\t}\n\n\t\t\treturn runeNames, shared\n\t\t})\n\t\to.rl, err = readline.NewEx(cfg)\n\t\tif err != nil {\n\t\t\treturn \"\", err\n\t\t}\n\t\to.historyFile = historyFile\n\t}\n\n\t// inject completer to autocompleter\n\to.completerFn = opts.CompleteFn\n\n\to.rl.SetPrompt(opts.Prompt)\n\tline, err := o.rl.Readline()\n\tif errors.Is(err, readline.ErrInterrupt) {\n\t\treturn \"\", interp.ErrInterrupt\n\t} else if errors.Is(err, io.EOF) {\n\t\treturn \"\", interp.ErrEOF\n\t} else if err != nil {\n\t\treturn \"\", err\n\t}\n\n\treturn line, nil\n}\n\nfunc (o *stdOS) History() ([]string, error) {\n\t// TODO: refactor history handling to use internal fs?\n\tr, err := os.Open(o.historyFile)\n\tif err != nil {\n\t\treturn nil, err\n\t}\n\tdefer r.Close()\n\tvar hs []string\n\tlineScanner := bufio.NewScanner(r)\n\tfor lineScanner.Scan() {\n\t\ths = append(hs, lineScanner.Text())\n\t}\n\tif err := lineScanner.Err(); err != nil {\n\t\treturn nil, err\n\t}\n\treturn hs, nil\n}\n\nfunc (o *stdOS) Close() error {\n\t// only close if is terminal otherwise ansi reset will write\n\t// to stdout and mess up raw output\n\tif o.rl != nil {\n\t\to.rl.Close()\n\t}\n\tclose(o.closeChan)\n\treturn nil\n}\n\nfunc Main(r *interp.Registry, version string) {\n\tos.Exit(func() int {\n\t\tdefer maybeProfile()()\n\t\tmaybeLogFile()\n\n\t\tsos := newStandardOS()\n\t\tdefer sos.Close()\n\t\ti, err := interp.New(sos, r)\n\t\tdefer i.Stop()\n\t\tif err != nil {\n\t\t\tfmt.Fprintln(sos.Stderr(), err)\n\t\t\treturn 1\n\t\t}\n\n\t\tif err := i.Main(context.Background(), sos.Stdout(), version); err != nil {\n\t\t\tif ex, ok := err.(interp.Exiter); ok {\n\t\t\t\treturn ex.ExitCode()\n\t\t\t}\n\t\t\treturn 1\n\t\t}\n\n\t\treturn 0\n\t}())\n}\n"},"lineMatches":[{"preview":"func Main(r *interp.Registry, version string) {","lineNumber":263,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/gardener/etcd-backup-restore"},"file":{"path":"vendor/github.com/google/gnostic-models/extensions/extensions.go","url":"/github.com/gardener/etcd-backup-restore/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go","content":"// Copyright 2017 Google LLC. All Rights Reserved.\n//\n// Licensed under the Apache License, Version 2.0 (the \"License\");\n// you may not use this file except in compliance with the License.\n// You may obtain a copy of the License at\n//\n// http://www.apache.org/licenses/LICENSE-2.0\n//\n// Unless required by applicable law or agreed to in writing, software\n// distributed under the License is distributed on an \"AS IS\" BASIS,\n// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n// See the License for the specific language governing permissions and\n// limitations under the License.\n\npackage gnostic_extension_v1\n\nimport (\n\t\"io/ioutil\"\n\t\"log\"\n\t\"os\"\n\n\t\"google.golang.org/protobuf/proto\"\n\t\"google.golang.org/protobuf/types/known/anypb\"\n)\n\ntype extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\n\n// Main implements the main program of an extension handler.\nfunc Main(handler extensionHandler) {\n\t// unpack the request\n\tdata, err := ioutil.ReadAll(os.Stdin)\n\tif err != nil {\n\t\tlog.Println(\"File error:\", err.Error())\n\t\tos.Exit(1)\n\t}\n\tif len(data) == 0 {\n\t\tlog.Println(\"No input data.\")\n\t\tos.Exit(1)\n\t}\n\trequest := \u0026ExtensionHandlerRequest{}\n\terr = proto.Unmarshal(data, request)\n\tif err != nil {\n\t\tlog.Println(\"Input error:\", err.Error())\n\t\tos.Exit(1)\n\t}\n\t// call the handler\n\thandled, output, err := handler(request.Wrapper.ExtensionName, request.Wrapper.Yaml)\n\t// respond with the output of the handler\n\tresponse := \u0026ExtensionHandlerResponse{\n\t\tHandled: false, // default assumption\n\t\tErrors: make([]string, 0),\n\t}\n\tif err != nil {\n\t\tresponse.Errors = append(response.Errors, err.Error())\n\t} else if handled {\n\t\tresponse.Handled = true\n\t\tresponse.Value, err = anypb.New(output)\n\t\tif err != nil {\n\t\t\tresponse.Errors = append(response.Errors, err.Error())\n\t\t}\n\t}\n\tresponseBytes, _ := proto.Marshal(response)\n\tos.Stdout.Write(responseBytes)\n}\n"},"lineMatches":[{"preview":"func Main(handler extensionHandler) {","lineNumber":28,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/driver.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n// Package driver provides the default driver for accessing a screen.\npackage driver // import \"golang.org/x/exp/shiny/driver\"\n\n// TODO: figure out what to say about the responsibility for users of this\n// package to check any implicit dependencies'' LICENSEs. For example, the\n// driver might use third party software outside of golang.org/x, like an X11\n// or OpenGL library.\n\nimport (\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\n// Main is called by the program''s main function to run the graphical\n// application.\n//\n// It calls f on the Screen, possibly in a separate goroutine, as some OS-\n// specific libraries require being on ''the main thread''. It returns when f\n// returns.\nfunc Main(f func(screen.Screen)) {\n\tmain(f)\n}\n"},"lineMatches":[{"preview":"func Main(f func(screen.Screen)) {","lineNumber":22,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/windriver/other.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/windriver/other.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build !windows\n\npackage windriver\n\nimport (\n\t\"fmt\"\n\t\"runtime\"\n\n\t\"golang.org/x/exp/shiny/driver/internal/errscreen\"\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\n// Main is called by the program''s main function to run the graphical\n// application.\n//\n// It calls f on the Screen, possibly in a separate goroutine, as some OS-\n// specific libraries require being on ''the main thread''. It returns when f\n// returns.\nfunc Main(f func(screen.Screen)) {\n\tf(errscreen.Stub(fmt.Errorf(\n\t\t\"windriver: unsupported GOOS/GOARCH %s/%s\", runtime.GOOS, runtime.GOARCH)))\n}\n"},"lineMatches":[{"preview":"func Main(f func(screen.Screen)) {","lineNumber":22,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/gldriver/gldriver.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/gldriver.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n// Package gldriver provides an OpenGL driver for accessing a screen.\npackage gldriver // import \"golang.org/x/exp/shiny/driver/gldriver\"\n\nimport (\n\t\"encoding/binary\"\n\t\"fmt\"\n\t\"math\"\n\n\t\"golang.org/x/exp/shiny/driver/internal/errscreen\"\n\t\"golang.org/x/exp/shiny/screen\"\n\t\"golang.org/x/image/math/f64\"\n\t\"golang.org/x/mobile/gl\"\n)\n\n// Main is called by the program''s main function to run the graphical\n// application.\n//\n// It calls f on the Screen, possibly in a separate goroutine, as some OS-\n// specific libraries require being on ''the main thread''. It returns when f\n// returns.\nfunc Main(f func(screen.Screen)) {\n\tif err := main(f); err != nil {\n\t\tf(errscreen.Stub(err))\n\t}\n}\n\nfunc mul(a, b f64.Aff3) f64.Aff3 {\n\treturn f64.Aff3{\n\t\ta[0]*b[0] + a[1]*b[3],\n\t\ta[0]*b[1] + a[1]*b[4],\n\t\ta[0]*b[2] + a[1]*b[5] + a[2],\n\n\t\ta[3]*b[0] + a[4]*b[3],\n\t\ta[3]*b[1] + a[4]*b[4],\n\t\ta[3]*b[2] + a[4]*b[5] + a[5],\n\t}\n}\n\n// writeAff3 must only be called while holding windowImpl.glctxMu.\nfunc writeAff3(glctx gl.Context, u gl.Uniform, a f64.Aff3) {\n\tvar m [9]float32\n\tm[0*3+0] = float32(a[0*3+0])\n\tm[0*3+1] = float32(a[1*3+0])\n\tm[0*3+2] = 0\n\tm[1*3+0] = float32(a[0*3+1])\n\tm[1*3+1] = float32(a[1*3+1])\n\tm[1*3+2] = 0\n\tm[2*3+0] = float32(a[0*3+2])\n\tm[2*3+1] = float32(a[1*3+2])\n\tm[2*3+2] = 1\n\tglctx.UniformMatrix3fv(u, m[:])\n}\n\n// f32Bytes returns the byte representation of float32 values in the given byte\n// order. byteOrder must be either binary.BigEndian or binary.LittleEndian.\nfunc f32Bytes(byteOrder binary.ByteOrder, values ...float32) []byte {\n\tle := false\n\tswitch byteOrder {\n\tcase binary.BigEndian:\n\tcase binary.LittleEndian:\n\t\tle = true\n\tdefault:\n\t\tpanic(fmt.Sprintf(\"invalid byte order %v\", byteOrder))\n\t}\n\n\tb := make([]byte, 4*len(values))\n\tfor i, v := range values {\n\t\tu := math.Float32bits(v)\n\t\tif le {\n\t\t\tb[4*i+0] = byte(u \u003e\u003e 0)\n\t\t\tb[4*i+1] = byte(u \u003e\u003e 8)\n\t\t\tb[4*i+2] = byte(u \u003e\u003e 16)\n\t\t\tb[4*i+3] = byte(u \u003e\u003e 24)\n\t\t} else {\n\t\t\tb[4*i+0] = byte(u \u003e\u003e 24)\n\t\t\tb[4*i+1] = byte(u \u003e\u003e 16)\n\t\t\tb[4*i+2] = byte(u \u003e\u003e 8)\n\t\t\tb[4*i+3] = byte(u \u003e\u003e 0)\n\t\t}\n\t}\n\treturn b\n}\n\n// compileProgram must only be called while holding windowImpl.glctxMu.\nfunc compileProgram(glctx gl.Context, vSrc, fSrc string) (gl.Program, error) {\n\tprogram := glctx.CreateProgram()\n\tif program.Value == 0 {\n\t\treturn gl.Program{}, fmt.Errorf(\"gldriver: no programs available\")\n\t}\n\n\tvertexShader, err := compileShader(glctx, gl.VERTEX_SHADER, vSrc)\n\tif err != nil {\n\t\treturn gl.Program{}, err\n\t}\n\tfragmentShader, err := compileShader(glctx, gl.FRAGMENT_SHADER, fSrc)\n\tif err != nil {\n\t\tglctx.DeleteShader(vertexShader)\n\t\treturn gl.Program{}, err\n\t}\n\n\tglctx.AttachShader(program, vertexShader)\n\tglctx.AttachShader(program, fragmentShader)\n\tglctx.LinkProgram(program)\n\n\t// Flag shaders for deletion when program is unlinked.\n\tglctx.DeleteShader(vertexShader)\n\tglctx.DeleteShader(fragmentShader)\n\n\tif glctx.GetProgrami(program, gl.LINK_STATUS) == 0 {\n\t\tdefer glctx.DeleteProgram(program)\n\t\treturn gl.Program{}, fmt.Errorf(\"gldriver: program compile: %s\", glctx.GetProgramInfoLog(program))\n\t}\n\treturn program, nil\n}\n\n// compileShader must only be called while holding windowImpl.glctxMu.\nfunc compileShader(glctx gl.Context, shaderType gl.Enum, src string) (gl.Shader, error) {\n\tshader := glctx.CreateShader(shaderType)\n\tif shader.Value == 0 {\n\t\treturn gl.Shader{}, fmt.Errorf(\"gldriver: could not create shader (type %v)\", shaderType)\n\t}\n\tglctx.ShaderSource(shader, src)\n\tglctx.CompileShader(shader)\n\tif glctx.GetShaderi(shader, gl.COMPILE_STATUS) == 0 {\n\t\tdefer glctx.DeleteShader(shader)\n\t\treturn gl.Shader{}, fmt.Errorf(\"gldriver: shader compile: %s\", glctx.GetShaderInfoLog(shader))\n\t}\n\treturn shader, nil\n}\n"},"lineMatches":[{"preview":"func Main(f func(screen.Screen)) {","lineNumber":24,"offsetAndLengths":[[0,10]]}]}]}}}}'

160 headers:

174 headers:

161 Content-Type:

175 Content-Type:

162 - application/json

176 - application/json

163 status: 200 OK

177 status: 200 OK

164 code: 200

178 code: 200

165− duration: 1.359880875s

179+ duration: 1.468141667s

166- id: 3

180- id: 3

167 request:

181 request:

168 proto: HTTP/1.1

182 proto: HTTP/1.1

169 proto_major: 1

183 proto_major: 1

170 proto_minor: 1

184 proto_minor: 1

171− content_length: 33189

185+ content_length: 39406

172 host: ""

186 host: ""

173− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_AJDsEhKmOO55HF5w0B78Wl2C\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go \\\\\\\"func main\\\\\\\" type:file select:file count:10\\\"}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 10 matches across 10 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/inancgumus/learngo/translation/chinese/02-编写第一个程序/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go\\n\\n## Result 2: github.com/inancgumus/learngo/first/first/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/first/first/main.go\\n\\n## Result 3: github.com/inancgumus/learngo/translation/spanish/02-tu-primer-programa/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/translation/spanish/02-tu-primer-programa/main.go\\n\\n## Result 4: github.com/inancgumus/learngo/02-write-your-first-program/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/02-write-your-first-program/main.go\\n\\n## Result 5: github.com/Go-Learning-Land/Go-Learning-Archive/GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go\\n\\nURL: /github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go\\n\\n## Result 6: github.com/Go-Learning-Land/Go-Learning-Archive/GolangBasics/learngo/translation/chinese/02-编写第一个程序/main.go\\n\\nURL: /github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go\\n\\n## Result 7: github.com/Go-Learning-Land/Go-Learning-Archive/GolangBasics/learngo/first/first/main.go\\n\\nURL: /github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/first/first/main.go\\n\\n## Result 8: github.com/Go-Learning-Land/Go-Learning-Archive/GolangBasics/learngo/02-write-your-first-program/main.go\\n\\nURL: /github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/02-write-your-first-program/main.go\\n\\n## Result 9: github.com/aditya43/golang-101/002-First-Program/main.go\\n\\nURL: /github.com/aditya43/golang-101/-/blob/002-First-Program/main.go\\n\\n## Result 10: github.com/golang/appengine/cmd/aebundler/aebundler.go\\n\\nURL: /github.com/golang/appengine/-/blob/cmd/aebundler/aebundler.go\\n\\n\",\"tool_call_id\":\"call_AJDsEhKmOO55HF5w0B78Wl2C\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

187+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_eG1GRwBeCLOUWghVcDdwhumF\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go content:\\\\\\\"func main(\\\\\\\" type:file count:10\\\",\\\"count\\\":10,\\\"timeout\\\":60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 10 matches across 10 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/yinchengtsinghua/go-ethereum-chinese/cmd/wnode/main.go\\n\\nURL: /github.com/yinchengtsinghua/go-ethereum-chinese/-/blob/cmd/wnode/main.go\\n\\n```\\n106| \\targServerPoW = flag.Float64(\\\"mspow\\\", whisper.DefaultMinimumPoW, \\\"PoW requirement for Mail Server request\\\")\\n107| \\n108| \\targIP = flag.String(\\\"ip\\\", \\\"\\\", \\\"IP address and port of this node (e.g. 127.0.0.1:30303)\\\")\\n109| \\targPub = flag.String(\\\"pub\\\", \\\"\\\", \\\"public key for asymmetric encryption\\\")\\n110| \\targDBPath = flag.String(\\\"dbpath\\\", \\\"\\\", \\\"path to the server's DB directory\\\")\\n111| \\targIDFile = flag.String(\\\"idfile\\\", \\\"\\\", \\\"file name with node id (private key)\\\")\\n112| argEnode = flag.String(\\\"boot\\\", \\\"\\\", \\\"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\\n113| \\targTopic = flag.String(\\\"topic\\\", \\\"\\\", \\\"topic in hexadecimal format (e.g. 70a4beef)\\\")\\n114| \\targSaveDir = flag.String(\\\"savedir\\\", \\\"\\\", \\\"directory where all incoming messages will be saved as files\\\")\\n115| )\\n116| func main() {\\n117| func main() {\\n118| \\tprocessArgs()\\n119| \\tinitialize()\\n120| \\trun()\\n121| \\tshutdown()\\n122| }\\n123| \\n124| func processArgs() {\\n125| \\tflag.Parse()\\n126| \\n```\\n\\n## Result 2: github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/cmd/wnode/main.go\\n\\nURL: /github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/-/blob/cmd/wnode/main.go\\n\\n```\\n106| \\targServerPoW = flag.Float64(\\\"mspow\\\", whisper.DefaultMinimumPoW, \\\"PoW requirement for Mail Server request\\\")\\n107| \\n108| \\targIP = flag.String(\\\"ip\\\", \\\"\\\", \\\"IP address and port of this node (e.g. 127.0.0.1:30303)\\\")\\n109| \\targPub = flag.String(\\\"pub\\\", \\\"\\\", \\\"public key for asymmetric encryption\\\")\\n110| \\targDBPath = flag.String(\\\"dbpath\\\", \\\"\\\", \\\"path to the server's DB directory\\\")\\n111| \\targIDFile = flag.String(\\\"idfile\\\", \\\"\\\", \\\"file name with node id (private key)\\\")\\n112| argEnode = flag.String(\\\"boot\\\", \\\"\\\", \\\"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\\n113| \\targTopic = flag.String(\\\"topic\\\", \\\"\\\", \\\"topic in hexadecimal format (e.g. 70a4beef)\\\")\\n114| \\targSaveDir = flag.String(\\\"savedir\\\", \\\"\\\", \\\"directory where all incoming messages will be saved as files\\\")\\n115| )\\n116| func main() {\\n117| func main() {\\n118| \\tprocessArgs()\\n119| \\tinitialize()\\n120| \\trun()\\n121| \\tshutdown()\\n122| }\\n123| \\n124| func processArgs() {\\n125| \\tflag.Parse()\\n126| \\n```\\n\\n## Result 3: github.com/erigontech/erigon/cmd/evm/internal/t8ntool/transition.go\\n\\nURL: /github.com/erigontech/erigon/-/blob/cmd/evm/internal/t8ntool/transition.go\\n\\n```\\n91| // compile-time conformance test\\n92| var (\\n93| \\t_ cli.ExitCoder = (*NumberedError)(nil)\\n94| )\\n95| \\n96| type input struct {\\n97| \\tAlloc types.GenesisAlloc `json:\\\"alloc,omitempty\\\"`\\n98| \\tEnv *stEnv `json:\\\"env,omitempty\\\"`\\n99| \\tTxs []*txWithKey `json:\\\"txs,omitempty\\\"`\\n100| }\\n101| func Main(ctx *cli.Context) error {\\n102| func Main(ctx *cli.Context) error {\\n103| \\tlog.Root().SetHandler(log.LvlFilterHandler(log.LvlInfo, log.StderrHandler))\\n104| \\tvar (\\n105| \\t\\terr error\\n106| \\t\\tbaseDir = \\\"\\\"\\n107| \\t)\\n108| \\tvar getTracer func(txIndex int, txHash common.Hash) (*tracing.Hooks, error)\\n109| \\n110| \\t// If user specified a basedir, make sure it exists\\n111| \\tif ctx.IsSet(OutputBasedir.Name) {\\n```\\n\\n## Result 4: github.com/cilium/hubble/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\nURL: /github.com/cilium/hubble/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\n```\\n18| \\t\\\"io/ioutil\\\"\\n19| \\t\\\"log\\\"\\n20| \\t\\\"os\\\"\\n21| \\n22| \\t\\\"google.golang.org/protobuf/proto\\\"\\n23| \\t\\\"google.golang.org/protobuf/types/known/anypb\\\"\\n24| )\\n25| \\n26| type extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\\n27| \\n28| func Main(handler extensionHandler) {\\n29| func Main(handler extensionHandler) {\\n30| \\t// unpack the request\\n31| \\tdata, err := ioutil.ReadAll(os.Stdin)\\n32| \\tif err != nil {\\n33| \\t\\tlog.Println(\\\"File error:\\\", err.Error())\\n34| \\t\\tos.Exit(1)\\n35| \\t}\\n36| \\tif len(data) == 0 {\\n37| \\t\\tlog.Println(\\\"No input data.\\\")\\n38| \\t\\tos.Exit(1)\\n```\\n\\n## Result 5: github.com/eclipse-che/che-operator/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\nURL: /github.com/eclipse-che/che-operator/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\n```\\n18| \\t\\\"io/ioutil\\\"\\n19| \\t\\\"log\\\"\\n20| \\t\\\"os\\\"\\n21| \\n22| \\t\\\"google.golang.org/protobuf/proto\\\"\\n23| \\t\\\"google.golang.org/protobuf/types/known/anypb\\\"\\n24| )\\n25| \\n26| type extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\\n27| \\n28| func Main(handler extensionHandler) {\\n29| func Main(handler extensionHandler) {\\n30| \\t// unpack the request\\n31| \\tdata, err := ioutil.ReadAll(os.Stdin)\\n32| \\tif err != nil {\\n33| \\t\\tlog.Println(\\\"File error:\\\", err.Error())\\n34| \\t\\tos.Exit(1)\\n35| \\t}\\n36| \\tif len(data) == 0 {\\n37| \\t\\tlog.Println(\\\"No input data.\\\")\\n38| \\t\\tos.Exit(1)\\n```\\n\\n## Result 6: github.com/wader/fq/pkg/cli/cli.go\\n\\nURL: /github.com/wader/fq/-/blob/pkg/cli/cli.go\\n\\n```\\n253| \\n254| func (o *stdOS) Close() error {\\n255| \\t// only close if is terminal otherwise ansi reset will write\\n256| \\t// to stdout and mess up raw output\\n257| \\tif o.rl != nil {\\n258| \\t\\to.rl.Close()\\n259| \\t}\\n260| \\tclose(o.closeChan)\\n261| \\treturn nil\\n262| }\\n263| func Main(r *interp.Registry, version string) {\\n264| func Main(r *interp.Registry, version string) {\\n265| \\tos.Exit(func() int {\\n266| \\t\\tdefer maybeProfile()()\\n267| \\t\\tmaybeLogFile()\\n268| \\n269| \\t\\tsos := newStandardOS()\\n270| \\t\\tdefer sos.Close()\\n271| \\t\\ti, err := interp.New(sos, r)\\n272| \\t\\tdefer i.Stop()\\n273| \\t\\tif err != nil {\\n```\\n\\n## Result 7: github.com/gardener/etcd-backup-restore/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\nURL: /github.com/gardener/etcd-backup-restore/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\n```\\n18| \\t\\\"io/ioutil\\\"\\n19| \\t\\\"log\\\"\\n20| \\t\\\"os\\\"\\n21| \\n22| \\t\\\"google.golang.org/protobuf/proto\\\"\\n23| \\t\\\"google.golang.org/protobuf/types/known/anypb\\\"\\n24| )\\n25| \\n26| type extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\\n27| \\n28| func Main(handler extensionHandler) {\\n29| func Main(handler extensionHandler) {\\n30| \\t// unpack the request\\n31| \\tdata, err := ioutil.ReadAll(os.Stdin)\\n32| \\tif err != nil {\\n33| \\t\\tlog.Println(\\\"File error:\\\", err.Error())\\n34| \\t\\tos.Exit(1)\\n35| \\t}\\n36| \\tif len(data) == 0 {\\n37| \\t\\tlog.Println(\\\"No input data.\\\")\\n38| \\t\\tos.Exit(1)\\n```\\n\\n## Result 8: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/driver.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver.go\\n\\n```\\n12| \\n13| import (\\n14| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n15| )\\n16| \\n17| // Main is called by the program's main function to run the graphical\\n18| // application.\\n19| //\\n20| // It calls f on the Screen, possibly in a separate goroutine, as some OS-\\n21| // specific libraries require being on 'the main thread'. It returns when f\\n22| func Main(f func(screen.Screen)) {\\n23| func Main(f func(screen.Screen)) {\\n24| \\tmain(f)\\n25| }\\n26| \\n```\\n\\n## Result 9: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/windriver/other.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/windriver/other.go\\n\\n```\\n12| \\n13| \\t\\\"golang.org/x/exp/shiny/driver/internal/errscreen\\\"\\n14| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n15| )\\n16| \\n17| // Main is called by the program's main function to run the graphical\\n18| // application.\\n19| //\\n20| // It calls f on the Screen, possibly in a separate goroutine, as some OS-\\n21| // specific libraries require being on 'the main thread'. It returns when f\\n22| func Main(f func(screen.Screen)) {\\n23| func Main(f func(screen.Screen)) {\\n24| \\tf(errscreen.Stub(fmt.Errorf(\\n25| \\t\\t\\\"windriver: unsupported GOOS/GOARCH %s/%s\\\", runtime.GOOS, runtime.GOARCH)))\\n26| }\\n27| \\n```\\n\\n## Result 10: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/gldriver/gldriver.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/gldriver.go\\n\\n```\\n14| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n15| \\t\\\"golang.org/x/image/math/f64\\\"\\n16| \\t\\\"golang.org/x/mobile/gl\\\"\\n17| )\\n18| \\n19| // Main is called by the program's main function to run the graphical\\n20| // application.\\n21| //\\n22| // It calls f on the Screen, possibly in a separate goroutine, as some OS-\\n23| // specific libraries require being on 'the main thread'. It returns when f\\n24| func Main(f func(screen.Screen)) {\\n25| func Main(f func(screen.Screen)) {\\n26| \\tif err := main(f); err != nil {\\n27| \\t\\tf(errscreen.Stub(err))\\n28| \\t}\\n29| }\\n30| \\n31| func mul(a, b f64.Aff3) f64.Aff3 {\\n32| \\treturn f64.Aff3{\\n33| \\t\\ta[0]*b[0] + a[1]*b[3],\\n34| \\t\\ta[0]*b[1] + a[1]*b[4],\\n```\\n\\n\",\"tool_call_id\":\"call_eG1GRwBeCLOUWghVcDdwhumF\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

174 headers:

188 headers:

175 Accept:

189 Accept:

176 - application/json

190 - application/json

177 Content-Type:

191 Content-Type:

178 - application/json

192 - application/json

179 User-Agent:

193 User-Agent:

180− - OpenAI/Go 2.3.0

194+ - OpenAI/Go 2.7.1

181 url: https://api.openai.com/v1/chat/completions

195 url: https://api.openai.com/v1/chat/completions

182 method: POST

196 method: POST

183 response:

197 response:

@@ -186,195 +200,182 @@ interactions:

186 proto_minor: 0

200 proto_minor: 0

187 content_length: -1

201 content_length: -1

188 body: |+

202 body: |+

189− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"qSXZQ09JkZ"}

203+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_zCYl929MzrVvYZ0oepRDlj2S","type":"function","function":{"name":"sourcegraph","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"nsxID"}

190−

191− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}],"usage":null,"obfuscation":"K93RWCy"}

192−

193− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"ttEJ11ACUOs"}

194−

195− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"10"},"finish_reason":null}],"usage":null,"obfuscation":"tR453HuS5g"}

196−

197− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" files"},"finish_reason":null}],"usage":null,"obfuscation":"oJfmJ3"}

198−

199− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" ("},"finish_reason":null}],"usage":null,"obfuscation":"O3Km3cFE1Y"}

200−

201− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"limit"},"finish_reason":null}],"usage":null,"obfuscation":"n9tyrnm"}

202−

203− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":")."},"finish_reason":null}],"usage":null,"obfuscation":"tjGzDClyKh"}

204−

205− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" Query"},"finish_reason":null}],"usage":null,"obfuscation":"d62ZXQ"}

206−

207− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"sm0E0Fb6q9Y"}

208−

209− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" lang"},"finish_reason":null}],"usage":null,"obfuscation":"I9tIHpD"}

210−

211− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"QC0bRPvuSyQ"}

212−

213− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"0cOekk36Cn"}

214−

215− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" \""},"finish_reason":null}],"usage":null,"obfuscation":"vkxr0c8Wz"}

216−

217− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}],"usage":null,"obfuscation":"CZGJ80dd"}

218−

219− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"2BZHORV"}

220−

221− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\""},"finish_reason":null}],"usage":null,"obfuscation":"PGGe9361rU"}

222

204

223− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" type"},"finish_reason":null}],"usage":null,"obfuscation":"0FT5svN"}

205+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"oFOD6roIsF2HgvC"}

224

206

225− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":file"},"finish_reason":null}],"usage":null,"obfuscation":"xsOUGQf"}

207+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"query"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zhPUtIQSVYr2h"}

226

208

227− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" select"},"finish_reason":null}],"usage":null,"obfuscation":"wcwsF"}

209+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"xUAj0KA0hQXkc"}

228

210

229− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":file"},"finish_reason":null}],"usage":null,"obfuscation":"VKg2GvE"}

211+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lang"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5uH8RDQnIbY27i"}

230

212

231− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".\n"},"finish_reason":null}],"usage":null,"obfuscation":"JGCwYohji"}

213+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c"}

232

214

233− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Examples"},"finish_reason":null}],"usage":null,"obfuscation":"wdCO"}

215+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

234

216

235− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"rTWFMG7FJCG"}

217+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" case"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Na8zglqyVQOC5"}

236

218

237− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"pD7Sa"}

219+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b"}

238

220

239− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"535FqtvG"}

221+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"yes"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jHCGS8ZCgFhcN0w"}

240

222

241− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/in"},"finish_reason":null}],"usage":null,"obfuscation":"NpYVkluvx"}

223+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c50QwVTgap"}

242

224

243− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"anc"},"finish_reason":null}],"usage":null,"obfuscation":"hxt6hBYe3"}

225+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"KrvCZfXJtXp4y"}

244

226

245− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"gum"},"finish_reason":null}],"usage":null,"obfuscation":"pmf2ao2EB"}

227+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UbrFL6LDMr6s4n"}

246

228

247− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"us"},"finish_reason":null}],"usage":null,"obfuscation":"f0H7QXbR8I"}

229+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wEHBORSzpb56n"}

248

230

249− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"k75yTPxomrS"}

231+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PrLoIc5Bjblb9"}

250

232

251− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"lear"},"finish_reason":null}],"usage":null,"obfuscation":"w9veB94B"}

233+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" type"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4nDFWl8N1kcy3"}

252

234

253− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ngo"},"finish_reason":null}],"usage":null,"obfuscation":"JXVQp8urs"}

235+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VqCFj770NvTcR"}

254

236

255− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/..."},"finish_reason":null}],"usage":null,"obfuscation":"sHA87rJ4"}

237+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5lFN0wQOQ0N9"}

256

238

257− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"wDb62Q0JcHQ"}

239+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"S"}

258

240

259− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"main"},"finish_reason":null}],"usage":null,"obfuscation":"tN9X7vuQ"}

241+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

260

242

261− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"3zVQCmtB1"}

243+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"VKCGJxMSybXNn"}

262

244

263− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"Xy2AtZbhGkr"}

245+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oR1v9a6eS9s3R"}

264

246

265− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"ADtBO"}

247+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AI2aUJzSU6wigJw"}

266

248

267− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"5QSQL9JY"}

249+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

268

250

269− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"kk6MqHUykBe"}

251+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"j1oxBVTHSXwwm6K"}

270

252

271− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Go"},"finish_reason":null}],"usage":null,"obfuscation":"ywBR3vBbnN"}

253+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EuGdXE1LIct"}

272

254

273− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-L"},"finish_reason":null}],"usage":null,"obfuscation":"20j6R9YCuL"}

255+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WzDqg28ifVHiz93"}

274

256

275− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"earning"},"finish_reason":null}],"usage":null,"obfuscation":"OsBjK"}

257+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

276

258

277− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-L"},"finish_reason":null}],"usage":null,"obfuscation":"zvCZC5bcQt"}

259+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"h"}

278

260

279− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"and"},"finish_reason":null}],"usage":null,"obfuscation":"5iSKX164P"}

261+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

280

262

281− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"4oYxLXlnOl0"}

263+ data: {"id":"chatcmpl-CTnvjUPXNibJ315mMuq4UvyF4QCYK","object":"chat.completion.chunk","created":1761219479,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9260,"completion_tokens":302,"total_tokens":9562,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"z"}

282

264

283− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Go"},"finish_reason":null}],"usage":null,"obfuscation":"Gkl8rz9qlC"}

265+ data: [DONE]

284−

285− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-L"},"finish_reason":null}],"usage":null,"obfuscation":"WpOnQ8E0x4"}

286−

287− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"earning"},"finish_reason":null}],"usage":null,"obfuscation":"dfpyI"}

288−

289− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"uhMPiaEtZSu"}

290−

291− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Archive"},"finish_reason":null}],"usage":null,"obfuscation":"AECAA"}

292−

293− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/..."},"finish_reason":null}],"usage":null,"obfuscation":"b9LrXfJs"}

294−

295− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"39qpOrTcW8Q"}

296−

297− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"main"},"finish_reason":null}],"usage":null,"obfuscation":"4PNtjY0O"}

298−

299− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"aTNO4D8XN"}

300−

301− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"aVCkpd5rQWI"}

302−

303− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"ljvGh"}

304−

305− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"EklAzCv4"}

306−

307− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/ad"},"finish_reason":null}],"usage":null,"obfuscation":"DtWE8xR4Q"}

308−

309− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"itya"},"finish_reason":null}],"usage":null,"obfuscation":"uw00bN5W"}

310−

311− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"43"},"finish_reason":null}],"usage":null,"obfuscation":"VlNrY7tSgM"}

312−

313− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/g"},"finish_reason":null}],"usage":null,"obfuscation":"abqldSxVsO"}

314−

315− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}],"usage":null,"obfuscation":"TD1snId"}

316−

317− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"k8ZTjn1j9bd"}

318−

319− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"101"},"finish_reason":null}],"usage":null,"obfuscation":"zbxhtJhY7"}

320−

321− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"GVV6QfFQvmx"}

322

266

323− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"002"},"finish_reason":null}],"usage":null,"obfuscation":"InVL162Di"}

267+ headers:

268+ Content-Type:

269+ - text/event-stream; charset=utf-8

270+ status: 200 OK

271+ code: 200

272+ duration: 7.457081916s

273+- id: 4

274+ request:

275+ proto: HTTP/1.1

276+ proto_major: 1

277+ proto_minor: 1

278+ content_length: 465

279+ host: sourcegraph.com

280+ body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go case:yes content:\"func main(\" type:file count:10"}}'

281+ headers:

282+ Content-Type:

283+ - application/json

284+ User-Agent:

285+ - crush/1.0

286+ url: https://sourcegraph.com/.api/graphql

287+ method: POST

288+ response:

289+ proto: HTTP/2.0

290+ proto_major: 2

291+ proto_minor: 0

292+ content_length: -1

293+ uncompressed: true

294+ body: '{"data":{"search":{"results":{"matchCount":10,"limitHit":true,"resultCount":10,"approximateResultCount":"10+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/yinchengtsinghua/go-ethereum-chinese"},"file":{"path":"cmd/wnode/main.go","url":"/github.com/yinchengtsinghua/go-ethereum-chinese/-/blob/cmd/wnode/main.go","content":"\n//此源码被清华学神尹成大魔王专业翻译分析并修改\n//尹成QQ77025077\n//尹成微信18510341407\n//尹成所在QQ群721929980\n//尹成邮箱 yinc13@mails.tsinghua.edu.cn\n//尹成毕业于清华大学,微软区块链领域全球最有价值专家\n//https://mvp.microsoft.com/zh-cn/PublicProfile/4033620\n//版权所有2017 Go Ethereum作者\n//此文件是Go以太坊的一部分。\n//\n//Go以太坊是免费软件：您可以重新发布和/或修改它\n//根据GNU通用公共许可证的条款\n//自由软件基金会，或者许可证的第3版，或者\n//（由您选择）任何更高版本。\n//\n//Go以太坊的分布希望它会有用，\n//但没有任何保证；甚至没有\n//适销性或特定用途的适用性。见\n//GNU通用公共许可证了解更多详细信息。\n//\n//你应该已经收到一份GNU通用公共许可证的副本\n//一起去以太坊吧。如果没有，请参见\u003chttp://www.gnu.org/licenses/\u003e。\n\n//这是一个简单的耳语节点。它可以用作独立的引导节点。\n//也可用于不同的测试和诊断目的。\n\npackage main\n\nimport (\n\t\"bufio\"\n\t\"crypto/ecdsa\"\n\tcrand \"crypto/rand\"\n\t\"crypto/sha512\"\n\t\"encoding/binary\"\n\t\"encoding/hex\"\n\t\"flag\"\n\t\"fmt\"\n\t\"io/ioutil\"\n\t\"os\"\n\t\"path/filepath\"\n\t\"strconv\"\n\t\"strings\"\n\t\"time\"\n\n\t\"github.com/ethereum/go-ethereum/cmd/utils\"\n\t\"github.com/ethereum/go-ethereum/common\"\n\t\"github.com/ethereum/go-ethereum/console\"\n\t\"github.com/ethereum/go-ethereum/crypto\"\n\t\"github.com/ethereum/go-ethereum/log\"\n\t\"github.com/ethereum/go-ethereum/p2p\"\n\t\"github.com/ethereum/go-ethereum/p2p/enode\"\n\t\"github.com/ethereum/go-ethereum/p2p/nat\"\n\t\"github.com/ethereum/go-ethereum/whisper/mailserver\"\n\twhisper \"github.com/ethereum/go-ethereum/whisper/whisperv6\"\n\t\"golang.org/x/crypto/pbkdf2\"\n)\n\nconst quitCommand = \"~Q\"\nconst entropySize = 32\n\n//独生子女\nvar (\n\tserver *p2p.Server\n\tshh *whisper.Whisper\n\tdone chan struct{}\n\tmailServer mailserver.WMailServer\n\tentropy [entropySize]byte\n\n\tinput = bufio.NewReader(os.Stdin)\n)\n\n//加密\nvar (\n\tsymKey []byte\n\tpub *ecdsa.PublicKey\n\tasymKey *ecdsa.PrivateKey\n\tnodeid *ecdsa.PrivateKey\n\ttopic whisper.TopicType\n\n\tasymKeyID string\n\tasymFilterID string\n\tsymFilterID string\n\tsymPass string\n\tmsPassword string\n)\n\n//CMD参数\nvar (\n\tbootstrapMode = flag.Bool(\"standalone\", false, \"boostrap node: don''t initiate connection to peers, just wait for incoming connections\")\n\tforwarderMode = flag.Bool(\"forwarder\", false, \"forwarder mode: only forward messages, neither encrypt nor decrypt messages\")\n\tmailServerMode = flag.Bool(\"mailserver\", false, \"mail server mode: delivers expired messages on demand\")\n\trequestMail = flag.Bool(\"mailclient\", false, \"request expired messages from the bootstrap server\")\n\tasymmetricMode = flag.Bool(\"asym\", false, \"use asymmetric encryption\")\n\tgenerateKey = flag.Bool(\"generatekey\", false, \"generate and show the private key\")\n\tfileExMode = flag.Bool(\"fileexchange\", false, \"file exchange mode\")\n\tfileReader = flag.Bool(\"filereader\", false, \"load and decrypt messages saved as files, display as plain text\")\n\ttestMode = flag.Bool(\"test\", false, \"use of predefined parameters for diagnostics (password, etc.)\")\n\techoMode = flag.Bool(\"echo\", false, \"echo mode: prints some arguments for diagnostics\")\n\n\targVerbosity = flag.Int(\"verbosity\", int(log.LvlError), \"log verbosity level\")\n\targTTL = flag.Uint(\"ttl\", 30, \"time-to-live for messages in seconds\")\n\targWorkTime = flag.Uint(\"work\", 5, \"work time in seconds\")\n\targMaxSize = flag.Uint(\"maxsize\", uint(whisper.DefaultMaxMessageSize), \"max size of message\")\n\targPoW = flag.Float64(\"pow\", whisper.DefaultMinimumPoW, \"PoW for normal messages in float format (e.g. 2.7)\")\n\targServerPoW = flag.Float64(\"mspow\", whisper.DefaultMinimumPoW, \"PoW requirement for Mail Server request\")\n\n\targIP = flag.String(\"ip\", \"\", \"IP address and port of this node (e.g. 127.0.0.1:30303)\")\n\targPub = flag.String(\"pub\", \"\", \"public key for asymmetric encryption\")\n\targDBPath = flag.String(\"dbpath\", \"\", \"path to the server''s DB directory\")\n\targIDFile = flag.String(\"idfile\", \"\", \"file name with node id (private key)\")\nargEnode = flag.String(\"boot\", \"\", \"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\n\targTopic = flag.String(\"topic\", \"\", \"topic in hexadecimal format (e.g. 70a4beef)\")\n\targSaveDir = flag.String(\"savedir\", \"\", \"directory where all incoming messages will be saved as files\")\n)\n\nfunc main() {\n\tprocessArgs()\n\tinitialize()\n\trun()\n\tshutdown()\n}\n\nfunc processArgs() {\n\tflag.Parse()\n\n\tif len(*argIDFile) \u003e 0 {\n\t\tvar err error\n\t\tnodeid, err = crypto.LoadECDSA(*argIDFile)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to load file [%s]: %s.\", *argIDFile, err)\n\t\t}\n\t}\n\nconst enodePrefix = \"enode://“\n\tif len(*argEnode) \u003e 0 {\n\t\tif (*argEnode)[:len(enodePrefix)] != enodePrefix {\n\t\t\t*argEnode = enodePrefix + *argEnode\n\t\t}\n\t}\n\n\tif len(*argTopic) \u003e 0 {\n\t\tx, err := hex.DecodeString(*argTopic)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to parse the topic: %s\", err)\n\t\t}\n\t\ttopic = whisper.BytesToTopic(x)\n\t}\n\n\tif *asymmetricMode \u0026\u0026 len(*argPub) \u003e 0 {\n\t\tvar err error\n\t\tif pub, err = crypto.UnmarshalPubkey(common.FromHex(*argPub)); err != nil {\n\t\t\tutils.Fatalf(\"invalid public key\")\n\t\t}\n\t}\n\n\tif len(*argSaveDir) \u003e 0 {\n\t\tif _, err := os.Stat(*argSaveDir); os.IsNotExist(err) {\n\t\t\tutils.Fatalf(\"Download directory ''%s'' does not exist\", *argSaveDir)\n\t\t}\n\t} else if *fileExMode {\n\t\tutils.Fatalf(\"Parameter ''savedir'' is mandatory for file exchange mode\")\n\t}\n\n\tif *echoMode {\n\t\techo()\n\t}\n}\n\nfunc echo() {\n\tfmt.Printf(\"ttl = %d \\n\", *argTTL)\n\tfmt.Printf(\"workTime = %d \\n\", *argWorkTime)\n\tfmt.Printf(\"pow = %f \\n\", *argPoW)\n\tfmt.Printf(\"mspow = %f \\n\", *argServerPoW)\n\tfmt.Printf(\"ip = %s \\n\", *argIP)\n\tfmt.Printf(\"pub = %s \\n\", common.ToHex(crypto.FromECDSAPub(pub)))\n\tfmt.Printf(\"idfile = %s \\n\", *argIDFile)\n\tfmt.Printf(\"dbpath = %s \\n\", *argDBPath)\n\tfmt.Printf(\"boot = %s \\n\", *argEnode)\n}\n\nfunc initialize() {\n\tlog.Root().SetHandler(log.LvlFilterHandler(log.Lvl(*argVerbosity), log.StreamHandler(os.Stderr, log.TerminalFormat(false))))\n\n\tdone = make(chan struct{})\n\tvar peers []*enode.Node\n\tvar err error\n\n\tif *generateKey {\n\t\tkey, err := crypto.GenerateKey()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate private key: %s\", err)\n\t\t}\n\t\tk := hex.EncodeToString(crypto.FromECDSA(key))\n\t\tfmt.Printf(\"Random private key: %s \\n\", k)\n\t\tos.Exit(0)\n\t}\n\n\tif *testMode {\nsymPass = \"wwww\" //ASCII码：0x77777777\n\t\tmsPassword = \"wwww\"\n\t}\n\n\tif *bootstrapMode {\n\t\tif len(*argIP) == 0 {\n\t\t\targIP = scanLineA(\"Please enter your IP and port (e.g. 127.0.0.1:30348): \")\n\t\t}\n\t} else if *fileReader {\n\t\t*bootstrapMode = true\n\t} else {\n\t\tif len(*argEnode) == 0 {\n\t\t\targEnode = scanLineA(\"Please enter the peer''s enode: \")\n\t\t}\n\t\tpeer := enode.MustParseV4(*argEnode)\n\t\tpeers = append(peers, peer)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tcfg := \u0026whisper.Config{\n\t\tMaxMessageSize: uint32(*argMaxSize),\n\t\tMinimumAcceptedPOW: *argPoW,\n\t}\n\n\tshh = whisper.New(cfg)\n\n\tif *argPoW != whisper.DefaultMinimumPoW {\n\t\terr := shh.SetMinimumPoW(*argPoW)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set PoW: %s\", err)\n\t\t}\n\t}\n\n\tif uint32(*argMaxSize) != whisper.DefaultMaxMessageSize {\n\t\terr := shh.SetMaxMessageSize(uint32(*argMaxSize))\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set max message size: %s\", err)\n\t\t}\n\t}\n\n\tasymKeyID, err = shh.NewKeyPair()\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t}\n\n\tasymKey, err = shh.GetPrivateKey(asymKeyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t}\n\n\tif nodeid == nil {\n\t\ttmpID, err := shh.NewKeyPair()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t\t}\n\n\t\tnodeid, err = shh.GetPrivateKey(tmpID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t\t}\n\t}\n\n\tmaxPeers := 80\n\tif *bootstrapMode {\n\t\tmaxPeers = 800\n\t}\n\n\t_, err = crand.Read(entropy[:])\n\tif err != nil {\n\t\tutils.Fatalf(\"crypto/rand failed: %s\", err)\n\t}\n\n\tif *mailServerMode {\n\t\tshh.RegisterServer(\u0026mailServer)\n\t\tif err := mailServer.Init(shh, *argDBPath, msPassword, *argServerPoW); err != nil {\n\t\t\tutils.Fatalf(\"Failed to init MailServer: %s\", err)\n\t\t}\n\t}\n\n\tserver = \u0026p2p.Server{\n\t\tConfig: p2p.Config{\n\t\t\tPrivateKey: nodeid,\n\t\t\tMaxPeers: maxPeers,\n\t\t\tName: common.MakeName(\"wnode\", \"6.0\"),\n\t\t\tProtocols: shh.Protocols(),\n\t\t\tListenAddr: *argIP,\n\t\t\tNAT: nat.Any(),\n\t\t\tBootstrapNodes: peers,\n\t\t\tStaticNodes: peers,\n\t\t\tTrustedNodes: peers,\n\t\t},\n\t}\n}\n\nfunc startServer() error {\n\terr := server.Start()\n\tif err != nil {\n\t\tfmt.Printf(\"Failed to start Whisper peer: %s.\", err)\n\t\treturn err\n\t}\n\n\tfmt.Printf(\"my public key: %s \\n\", common.ToHex(crypto.FromECDSAPub(\u0026asymKey.PublicKey)))\n\tfmt.Println(server.NodeInfo().Enode)\n\n\tif *bootstrapMode {\n\t\tconfigureNode()\n\t\tfmt.Println(\"Bootstrap Whisper node started\")\n\t} else {\n\t\tfmt.Println(\"Whisper node started\")\n//首先看看我们是否可以建立连接，然后请求用户输入\n\t\twaitForConnection(true)\n\t\tconfigureNode()\n\t}\n\n\tif *fileExMode {\n\t\tfmt.Printf(\"Please type the file name to be send. To quit type: ''%s''\\n\", quitCommand)\n\t} else if *fileReader {\n\t\tfmt.Printf(\"Please type the file name to be decrypted. To quit type: ''%s''\\n\", quitCommand)\n\t} else if !*forwarderMode {\n\t\tfmt.Printf(\"Please type the message. To quit type: ''%s''\\n\", quitCommand)\n\t}\n\treturn nil\n}\n\nfunc configureNode() {\n\tvar err error\n\tvar p2pAccept bool\n\n\tif *forwarderMode {\n\t\treturn\n\t}\n\n\tif *asymmetricMode {\n\t\tif len(*argPub) == 0 {\n\t\t\ts := scanLine(\"Please enter the peer''s public key: \")\n\t\t\tb := common.FromHex(s)\n\t\t\tif b == nil {\n\t\t\t\tutils.Fatalf(\"Error: can not convert hexadecimal string\")\n\t\t\t}\n\t\t\tif pub, err = crypto.UnmarshalPubkey(b); err != nil {\n\t\t\t\tutils.Fatalf(\"Error: invalid peer public key\")\n\t\t\t}\n\t\t}\n\t}\n\n\tif *requestMail {\n\t\tp2pAccept = true\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tif !*asymmetricMode \u0026\u0026 !*forwarderMode {\n\t\tif len(symPass) == 0 {\n\t\t\tsymPass, err = console.Stdin.PromptPassword(\"Please enter the password for symmetric encryption: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read passphrase: %v\", err)\n\t\t\t}\n\t\t}\n\n\t\tsymKeyID, err := shh.AddSymKeyFromPassword(symPass)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to create symmetric key: %s\", err)\n\t\t}\n\t\tsymKey, err = shh.GetSymKey(symKeyID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to save symmetric key: %s\", err)\n\t\t}\n\t\tif len(*argTopic) == 0 {\n\t\t\tgenerateTopic([]byte(symPass))\n\t\t}\n\n\t\tfmt.Printf(\"Filter is configured for the topic: %x \\n\", topic)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(*argDBPath) == 0 {\n\t\t\targDBPath = scanLineA(\"Please enter the path to DB file: \")\n\t\t}\n\t}\n\n\tsymFilter := whisper.Filter{\n\t\tKeySym: symKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tsymFilterID, err = shh.Subscribe(\u0026symFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n\n\tasymFilter := whisper.Filter{\n\t\tKeyAsym: asymKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tasymFilterID, err = shh.Subscribe(\u0026asymFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n}\n\nfunc generateTopic(password []byte) {\n\tx := pbkdf2.Key(password, password, 4096, 128, sha512.New)\n\tfor i := 0; i \u003c len(x); i++ {\n\t\ttopic[i%whisper.TopicLength] ^= x[i]\n\t}\n}\n\nfunc waitForConnection(timeout bool) {\n\tvar cnt int\n\tvar connected bool\n\tfor !connected {\n\t\ttime.Sleep(time.Millisecond * 50)\n\t\tconnected = server.PeerCount() \u003e 0\n\t\tif timeout {\n\t\t\tcnt++\n\t\t\tif cnt \u003e 1000 {\n\t\t\t\tutils.Fatalf(\"Timeout expired, failed to connect\")\n\t\t\t}\n\t\t}\n\t}\n\n\tfmt.Println(\"Connected to peer.\")\n}\n\nfunc run() {\n\terr := startServer()\n\tif err != nil {\n\t\treturn\n\t}\n\tdefer server.Stop()\n\tshh.Start(nil)\n\tdefer shh.Stop()\n\n\tif !*forwarderMode {\n\t\tgo messageLoop()\n\t}\n\n\tif *requestMail {\n\t\trequestExpiredMessagesLoop()\n\t} else if *fileExMode {\n\t\tsendFilesLoop()\n\t} else if *fileReader {\n\t\tfileReaderLoop()\n\t} else {\n\t\tsendLoop()\n\t}\n}\n\nfunc shutdown() {\n\tclose(done)\n\tmailServer.Close()\n}\n\nfunc sendLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tsendMsg([]byte(s))\n\t\tif *asymmetricMode {\n//为方便起见，请打印您自己的消息，\n//因为在非对称模式下是不可能解密的\n\t\t\ttimestamp := time.Now().Unix()\n\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: %s\\n\", timestamp, from, s)\n\t\t}\n\t}\n}\n\nfunc sendFilesLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tb, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\n\t\t\th := sendMsg(b)\n\t\t\tif (h == common.Hash{}) {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: message was not sent \\n\")\n\t\t\t} else {\n\t\t\t\ttimestamp := time.Now().Unix()\n\t\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: sent message with hash %x\\n\", timestamp, from, h)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc fileReaderLoop() {\n\twatcher1 := shh.GetFilter(symFilterID)\n\twatcher2 := shh.GetFilter(asymFilterID)\n\tif watcher1 == nil \u0026\u0026 watcher2 == nil {\n\t\tfmt.Println(\"Error: neither symmetric nor asymmetric filter is installed\")\n\t\treturn\n\t}\n\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\traw, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\nenv := whisper.Envelope{Data: raw} //主题为零\nmsg := env.Open(watcher1) //不管主题如何，都强制打开信封\n\t\t\tif msg == nil {\n\t\t\t\tmsg = env.Open(watcher2)\n\t\t\t}\n\t\t\tif msg == nil {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: failed to decrypt the message \\n\")\n\t\t\t} else {\n\t\t\t\tprintMessageInfo(msg)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc scanLine(prompt string) string {\n\tif len(prompt) \u003e 0 {\n\t\tfmt.Print(prompt)\n\t}\n\ttxt, err := input.ReadString(''\\n'')\n\tif err != nil {\n\t\tutils.Fatalf(\"input error: %s\", err)\n\t}\n\ttxt = strings.TrimRight(txt, \"\\n\\r\")\n\treturn txt\n}\n\nfunc scanLineA(prompt string) *string {\n\ts := scanLine(prompt)\n\treturn \u0026s\n}\n\nfunc scanUint(prompt string) uint32 {\n\ts := scanLine(prompt)\n\ti, err := strconv.Atoi(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Fail to parse the lower time limit: %s\", err)\n\t}\n\treturn uint32(i)\n}\n\nfunc sendMsg(payload []byte) common.Hash {\n\tparams := whisper.MessageParams{\n\t\tSrc: asymKey,\n\t\tDst: pub,\n\t\tKeySym: symKey,\n\t\tPayload: payload,\n\t\tTopic: topic,\n\t\tTTL: uint32(*argTTL),\n\t\tPoW: *argPoW,\n\t\tWorkTime: uint32(*argWorkTime),\n\t}\n\n\tmsg, err := whisper.NewSentMessage(\u0026params)\n\tif err != nil {\n\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t}\n\n\tenvelope, err := msg.Wrap(\u0026params)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to seal message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\terr = shh.Send(envelope)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to send message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\treturn envelope.Hash()\n}\n\nfunc messageLoop() {\n\tsf := shh.GetFilter(symFilterID)\n\tif sf == nil {\n\t\tutils.Fatalf(\"symmetric filter is not installed\")\n\t}\n\n\taf := shh.GetFilter(asymFilterID)\n\tif af == nil {\n\t\tutils.Fatalf(\"asymmetric filter is not installed\")\n\t}\n\n\tticker := time.NewTicker(time.Millisecond * 50)\n\n\tfor {\n\t\tselect {\n\t\tcase \u003c-ticker.C:\n\t\t\tm1 := sf.Retrieve()\n\t\t\tm2 := af.Retrieve()\n\t\t\tmessages := append(m1, m2...)\n\t\t\tfor _, msg := range messages {\n\t\t\t\treportedOnce := false\n\t\t\t\tif !*fileExMode \u0026\u0026 len(msg.Payload) \u003c= 2048 {\n\t\t\t\t\tprintMessageInfo(msg)\n\t\t\t\t\treportedOnce = true\n\t\t\t\t}\n\n//在指定argsavedir时保存所有消息。\n//FileExMode仅指定消息保存后如何显示在控制台上。\n//如果fileexmode==true，则只显示哈希值，因为消息可能太大。\n\t\t\t\tif len(*argSaveDir) \u003e 0 {\n\t\t\t\t\twriteMessageToFile(*argSaveDir, msg, !reportedOnce)\n\t\t\t\t}\n\t\t\t}\n\t\tcase \u003c-done:\n\t\t\treturn\n\t\t}\n\t}\n}\n\nfunc printMessageInfo(msg *whisper.ReceivedMessage) {\ntimestamp := fmt.Sprintf(\"%d\", msg.Sent) //用于诊断的Unix时间戳\n\ttext := string(msg.Payload)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tif whisper.IsPubKeyEqual(msg.Src, \u0026asymKey.PublicKey) {\nfmt.Printf(\"\\n%s \u003c%x\u003e: %s\\n\", timestamp, address, text) //我的信息\n\t} else {\nfmt.Printf(\"\\n%s [%x]: %s\\n\", timestamp, address, text) //来自对等方的消息\n\t}\n}\n\nfunc writeMessageToFile(dir string, msg *whisper.ReceivedMessage, show bool) {\n\tif len(dir) == 0 {\n\t\treturn\n\t}\n\n\ttimestamp := fmt.Sprintf(\"%d\", msg.Sent)\n\tname := fmt.Sprintf(\"%x\", msg.EnvelopeHash)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tenv := shh.GetEnvelope(msg.EnvelopeHash)\n\tif env == nil {\n\t\tfmt.Printf(\"\\nUnexpected error: envelope not found: %x\\n\", msg.EnvelopeHash)\n\t\treturn\n\t}\n\n//这是一个示例代码；如果不想保存自己的消息，请取消注释。\n//如果whisper.ispubkeyequal（msg.src，\u0026asymkey.publickey）\n//fmt.printf（“\\n%s\u003c%x\u003e：我收到的消息，未保存：“%s''\\n”，时间戳，地址，名称）\n//返回\n//}\n\n\tfullpath := filepath.Join(dir, name)\n\terr := ioutil.WriteFile(fullpath, env.Data, 0644)\n\tif err != nil {\n\t\tfmt.Printf(\"\\n%s {%x}: message received but not saved: %s\\n\", timestamp, address, err)\n\t} else if show {\n\t\tfmt.Printf(\"\\n%s {%x}: message received and saved as ''%s'' (%d bytes)\\n\", timestamp, address, name, len(env.Data))\n\t}\n}\n\nfunc requestExpiredMessagesLoop() {\n\tvar key, peerID, bloom []byte\n\tvar timeLow, timeUpp uint32\n\tvar t string\n\tvar xt whisper.TopicType\n\n\tkeyID, err := shh.AddSymKeyFromPassword(msPassword)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to create symmetric key for mail request: %s\", err)\n\t}\n\tkey, err = shh.GetSymKey(keyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to save symmetric key for mail request: %s\", err)\n\t}\n\tpeerID = extractIDFromEnode(*argEnode)\n\tshh.AllowP2PMessagesFromPeer(peerID)\n\n\tfor {\n\t\ttimeLow = scanUint(\"Please enter the lower limit of the time range (unix timestamp): \")\n\t\ttimeUpp = scanUint(\"Please enter the upper limit of the time range (unix timestamp): \")\n\t\tt = scanLine(\"Enter the topic (hex). Press enter to request all messages, regardless of the topic: \")\n\t\tif len(t) == whisper.TopicLength*2 {\n\t\t\tx, err := hex.DecodeString(t)\n\t\t\tif err != nil {\n\t\t\t\tfmt.Printf(\"Failed to parse the topic: %s \\n\", err)\n\t\t\t\tcontinue\n\t\t\t}\n\t\t\txt = whisper.BytesToTopic(x)\n\t\t\tbloom = whisper.TopicToBloom(xt)\n\t\t\tobfuscateBloom(bloom)\n\t\t} else if len(t) == 0 {\n\t\t\tbloom = whisper.MakeFullNodeBloom()\n\t\t} else {\n\t\t\tfmt.Println(\"Error: topic is invalid, request aborted\")\n\t\t\tcontinue\n\t\t}\n\n\t\tif timeUpp == 0 {\n\t\t\ttimeUpp = 0xFFFFFFFF\n\t\t}\n\n\t\tdata := make([]byte, 8, 8+whisper.BloomFilterSize)\n\t\tbinary.BigEndian.PutUint32(data, timeLow)\n\t\tbinary.BigEndian.PutUint32(data[4:], timeUpp)\n\t\tdata = append(data, bloom...)\n\n\t\tvar params whisper.MessageParams\n\t\tparams.PoW = *argServerPoW\n\t\tparams.Payload = data\n\t\tparams.KeySym = key\n\t\tparams.Src = asymKey\n\t\tparams.WorkTime = 5\n\n\t\tmsg, err := whisper.NewSentMessage(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t\t}\n\t\tenv, err := msg.Wrap(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Wrap failed: %s\", err)\n\t\t}\n\n\t\terr = shh.RequestHistoricMessages(peerID, env)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to send P2P message: %s\", err)\n\t\t}\n\n\t\ttime.Sleep(time.Second * 5)\n\t}\n}\n\nfunc extractIDFromEnode(s string) []byte {\n\tn, err := enode.ParseV4(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to parse enode: %s\", err)\n\t}\n\treturn n.ID().Bytes()\n}\n\n//模糊布卢姆增加16个随机位到布卢姆\n//筛选，以便混淆包含的主题。\n//它在每个会话中都具有确定性。\n//尽管有额外的位，它将平均匹配\n//比完整节点的Bloom过滤器少32000倍的消息。\nfunc obfuscateBloom(bloom []byte) {\n\tconst half = entropySize / 2\n\tfor i := 0; i \u003c half; i++ {\n\t\tx := int(entropy[i])\n\t\tif entropy[half+i] \u003c 128 {\n\t\t\tx += 256\n\t\t}\n\nbloom[x/8] = 1 \u003c\u003c uint(x%8) //设置位号x\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":116,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum"},"file":{"path":"cmd/wnode/main.go","url":"/github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/-/blob/cmd/wnode/main.go","content":"\n//此源码被清华学神尹成大魔王专业翻译分析并修改\n//尹成QQ77025077\n//尹成微信18510341407\n//尹成所在QQ群721929980\n//尹成邮箱 yinc13@mails.tsinghua.edu.cn\n//尹成毕业于清华大学,微软区块链领域全球最有价值专家\n//https://mvp.microsoft.com/zh-cn/PublicProfile/4033620\n//版权所有2017 Go Ethereum作者\n//此文件是Go以太坊的一部分。\n//\n//Go以太坊是免费软件：您可以重新发布和/或修改它\n//根据GNU通用公共许可证的条款\n//自由软件基金会，或者许可证的第3版，或者\n//（由您选择）任何更高版本。\n//\n//Go以太坊的分布希望它会有用，\n//但没有任何保证；甚至没有\n//适销性或特定用途的适用性。见\n//GNU通用公共许可证了解更多详细信息。\n//\n//你应该已经收到一份GNU通用公共许可证的副本\n//一起去以太坊吧。如果没有，请参见\u003chttp://www.gnu.org/licenses/\u003e。\n\n//这是一个简单的耳语节点。它可以用作独立的引导节点。\n//也可用于不同的测试和诊断目的。\n\npackage main\n\nimport (\n\t\"bufio\"\n\t\"crypto/ecdsa\"\n\tcrand \"crypto/rand\"\n\t\"crypto/sha512\"\n\t\"encoding/binary\"\n\t\"encoding/hex\"\n\t\"flag\"\n\t\"fmt\"\n\t\"io/ioutil\"\n\t\"os\"\n\t\"path/filepath\"\n\t\"strconv\"\n\t\"strings\"\n\t\"time\"\n\n\t\"github.com/ethereum/go-ethereum/cmd/utils\"\n\t\"github.com/ethereum/go-ethereum/common\"\n\t\"github.com/ethereum/go-ethereum/console\"\n\t\"github.com/ethereum/go-ethereum/crypto\"\n\t\"github.com/ethereum/go-ethereum/log\"\n\t\"github.com/ethereum/go-ethereum/p2p\"\n\t\"github.com/ethereum/go-ethereum/p2p/discover\"\n\t\"github.com/ethereum/go-ethereum/p2p/nat\"\n\t\"github.com/ethereum/go-ethereum/whisper/mailserver\"\n\twhisper \"github.com/ethereum/go-ethereum/whisper/whisperv6\"\n\t\"golang.org/x/crypto/pbkdf2\"\n)\n\nconst quitCommand = \"~Q\"\nconst entropySize = 32\n\n//独生子女\nvar (\n\tserver *p2p.Server\n\tshh *whisper.Whisper\n\tdone chan struct{}\n\tmailServer mailserver.WMailServer\n\tentropy [entropySize]byte\n\n\tinput = bufio.NewReader(os.Stdin)\n)\n\n//加密\nvar (\n\tsymKey []byte\n\tpub *ecdsa.PublicKey\n\tasymKey *ecdsa.PrivateKey\n\tnodeid *ecdsa.PrivateKey\n\ttopic whisper.TopicType\n\n\tasymKeyID string\n\tasymFilterID string\n\tsymFilterID string\n\tsymPass string\n\tmsPassword string\n)\n\n//CMD参数\nvar (\n\tbootstrapMode = flag.Bool(\"standalone\", false, \"boostrap node: don''t initiate connection to peers, just wait for incoming connections\")\n\tforwarderMode = flag.Bool(\"forwarder\", false, \"forwarder mode: only forward messages, neither encrypt nor decrypt messages\")\n\tmailServerMode = flag.Bool(\"mailserver\", false, \"mail server mode: delivers expired messages on demand\")\n\trequestMail = flag.Bool(\"mailclient\", false, \"request expired messages from the bootstrap server\")\n\tasymmetricMode = flag.Bool(\"asym\", false, \"use asymmetric encryption\")\n\tgenerateKey = flag.Bool(\"generatekey\", false, \"generate and show the private key\")\n\tfileExMode = flag.Bool(\"fileexchange\", false, \"file exchange mode\")\n\tfileReader = flag.Bool(\"filereader\", false, \"load and decrypt messages saved as files, display as plain text\")\n\ttestMode = flag.Bool(\"test\", false, \"use of predefined parameters for diagnostics (password, etc.)\")\n\techoMode = flag.Bool(\"echo\", false, \"echo mode: prints some arguments for diagnostics\")\n\n\targVerbosity = flag.Int(\"verbosity\", int(log.LvlError), \"log verbosity level\")\n\targTTL = flag.Uint(\"ttl\", 30, \"time-to-live for messages in seconds\")\n\targWorkTime = flag.Uint(\"work\", 5, \"work time in seconds\")\n\targMaxSize = flag.Uint(\"maxsize\", uint(whisper.DefaultMaxMessageSize), \"max size of message\")\n\targPoW = flag.Float64(\"pow\", whisper.DefaultMinimumPoW, \"PoW for normal messages in float format (e.g. 2.7)\")\n\targServerPoW = flag.Float64(\"mspow\", whisper.DefaultMinimumPoW, \"PoW requirement for Mail Server request\")\n\n\targIP = flag.String(\"ip\", \"\", \"IP address and port of this node (e.g. 127.0.0.1:30303)\")\n\targPub = flag.String(\"pub\", \"\", \"public key for asymmetric encryption\")\n\targDBPath = flag.String(\"dbpath\", \"\", \"path to the server''s DB directory\")\n\targIDFile = flag.String(\"idfile\", \"\", \"file name with node id (private key)\")\nargEnode = flag.String(\"boot\", \"\", \"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\n\targTopic = flag.String(\"topic\", \"\", \"topic in hexadecimal format (e.g. 70a4beef)\")\n\targSaveDir = flag.String(\"savedir\", \"\", \"directory where all incoming messages will be saved as files\")\n)\n\nfunc main() {\n\tprocessArgs()\n\tinitialize()\n\trun()\n\tshutdown()\n}\n\nfunc processArgs() {\n\tflag.Parse()\n\n\tif len(*argIDFile) \u003e 0 {\n\t\tvar err error\n\t\tnodeid, err = crypto.LoadECDSA(*argIDFile)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to load file [%s]: %s.\", *argIDFile, err)\n\t\t}\n\t}\n\nconst enodePrefix = \"enode://“\n\tif len(*argEnode) \u003e 0 {\n\t\tif (*argEnode)[:len(enodePrefix)] != enodePrefix {\n\t\t\t*argEnode = enodePrefix + *argEnode\n\t\t}\n\t}\n\n\tif len(*argTopic) \u003e 0 {\n\t\tx, err := hex.DecodeString(*argTopic)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to parse the topic: %s\", err)\n\t\t}\n\t\ttopic = whisper.BytesToTopic(x)\n\t}\n\n\tif *asymmetricMode \u0026\u0026 len(*argPub) \u003e 0 {\n\t\tvar err error\n\t\tif pub, err = crypto.UnmarshalPubkey(common.FromHex(*argPub)); err != nil {\n\t\t\tutils.Fatalf(\"invalid public key\")\n\t\t}\n\t}\n\n\tif len(*argSaveDir) \u003e 0 {\n\t\tif _, err := os.Stat(*argSaveDir); os.IsNotExist(err) {\n\t\t\tutils.Fatalf(\"Download directory ''%s'' does not exist\", *argSaveDir)\n\t\t}\n\t} else if *fileExMode {\n\t\tutils.Fatalf(\"Parameter ''savedir'' is mandatory for file exchange mode\")\n\t}\n\n\tif *echoMode {\n\t\techo()\n\t}\n}\n\nfunc echo() {\n\tfmt.Printf(\"ttl = %d \\n\", *argTTL)\n\tfmt.Printf(\"workTime = %d \\n\", *argWorkTime)\n\tfmt.Printf(\"pow = %f \\n\", *argPoW)\n\tfmt.Printf(\"mspow = %f \\n\", *argServerPoW)\n\tfmt.Printf(\"ip = %s \\n\", *argIP)\n\tfmt.Printf(\"pub = %s \\n\", common.ToHex(crypto.FromECDSAPub(pub)))\n\tfmt.Printf(\"idfile = %s \\n\", *argIDFile)\n\tfmt.Printf(\"dbpath = %s \\n\", *argDBPath)\n\tfmt.Printf(\"boot = %s \\n\", *argEnode)\n}\n\nfunc initialize() {\n\tlog.Root().SetHandler(log.LvlFilterHandler(log.Lvl(*argVerbosity), log.StreamHandler(os.Stderr, log.TerminalFormat(false))))\n\n\tdone = make(chan struct{})\n\tvar peers []*discover.Node\n\tvar err error\n\n\tif *generateKey {\n\t\tkey, err := crypto.GenerateKey()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate private key: %s\", err)\n\t\t}\n\t\tk := hex.EncodeToString(crypto.FromECDSA(key))\n\t\tfmt.Printf(\"Random private key: %s \\n\", k)\n\t\tos.Exit(0)\n\t}\n\n\tif *testMode {\nsymPass = \"wwww\" //ASCII码：0x77777777\n\t\tmsPassword = \"wwww\"\n\t}\n\n\tif *bootstrapMode {\n\t\tif len(*argIP) == 0 {\n\t\t\targIP = scanLineA(\"Please enter your IP and port (e.g. 127.0.0.1:30348): \")\n\t\t}\n\t} else if *fileReader {\n\t\t*bootstrapMode = true\n\t} else {\n\t\tif len(*argEnode) == 0 {\n\t\t\targEnode = scanLineA(\"Please enter the peer''s enode: \")\n\t\t}\n\t\tpeer := discover.MustParseNode(*argEnode)\n\t\tpeers = append(peers, peer)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tcfg := \u0026whisper.Config{\n\t\tMaxMessageSize: uint32(*argMaxSize),\n\t\tMinimumAcceptedPOW: *argPoW,\n\t}\n\n\tshh = whisper.New(cfg)\n\n\tif *argPoW != whisper.DefaultMinimumPoW {\n\t\terr := shh.SetMinimumPoW(*argPoW)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set PoW: %s\", err)\n\t\t}\n\t}\n\n\tif uint32(*argMaxSize) != whisper.DefaultMaxMessageSize {\n\t\terr := shh.SetMaxMessageSize(uint32(*argMaxSize))\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to set max message size: %s\", err)\n\t\t}\n\t}\n\n\tasymKeyID, err = shh.NewKeyPair()\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t}\n\n\tasymKey, err = shh.GetPrivateKey(asymKeyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t}\n\n\tif nodeid == nil {\n\t\ttmpID, err := shh.NewKeyPair()\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to generate a new key pair: %s\", err)\n\t\t}\n\n\t\tnodeid, err = shh.GetPrivateKey(tmpID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to retrieve a new key pair: %s\", err)\n\t\t}\n\t}\n\n\tmaxPeers := 80\n\tif *bootstrapMode {\n\t\tmaxPeers = 800\n\t}\n\n\t_, err = crand.Read(entropy[:])\n\tif err != nil {\n\t\tutils.Fatalf(\"crypto/rand failed: %s\", err)\n\t}\n\n\tif *mailServerMode {\n\t\tshh.RegisterServer(\u0026mailServer)\n\t\tif err := mailServer.Init(shh, *argDBPath, msPassword, *argServerPoW); err != nil {\n\t\t\tutils.Fatalf(\"Failed to init MailServer: %s\", err)\n\t\t}\n\t}\n\n\tserver = \u0026p2p.Server{\n\t\tConfig: p2p.Config{\n\t\t\tPrivateKey: nodeid,\n\t\t\tMaxPeers: maxPeers,\n\t\t\tName: common.MakeName(\"wnode\", \"6.0\"),\n\t\t\tProtocols: shh.Protocols(),\n\t\t\tListenAddr: *argIP,\n\t\t\tNAT: nat.Any(),\n\t\t\tBootstrapNodes: peers,\n\t\t\tStaticNodes: peers,\n\t\t\tTrustedNodes: peers,\n\t\t},\n\t}\n}\n\nfunc startServer() error {\n\terr := server.Start()\n\tif err != nil {\n\t\tfmt.Printf(\"Failed to start Whisper peer: %s.\", err)\n\t\treturn err\n\t}\n\n\tfmt.Printf(\"my public key: %s \\n\", common.ToHex(crypto.FromECDSAPub(\u0026asymKey.PublicKey)))\n\tfmt.Println(server.NodeInfo().Enode)\n\n\tif *bootstrapMode {\n\t\tconfigureNode()\n\t\tfmt.Println(\"Bootstrap Whisper node started\")\n\t} else {\n\t\tfmt.Println(\"Whisper node started\")\n//首先看看我们是否可以建立连接，然后请求用户输入\n\t\twaitForConnection(true)\n\t\tconfigureNode()\n\t}\n\n\tif *fileExMode {\n\t\tfmt.Printf(\"Please type the file name to be send. To quit type: ''%s''\\n\", quitCommand)\n\t} else if *fileReader {\n\t\tfmt.Printf(\"Please type the file name to be decrypted. To quit type: ''%s''\\n\", quitCommand)\n\t} else if !*forwarderMode {\n\t\tfmt.Printf(\"Please type the message. To quit type: ''%s''\\n\", quitCommand)\n\t}\n\treturn nil\n}\n\nfunc configureNode() {\n\tvar err error\n\tvar p2pAccept bool\n\n\tif *forwarderMode {\n\t\treturn\n\t}\n\n\tif *asymmetricMode {\n\t\tif len(*argPub) == 0 {\n\t\t\ts := scanLine(\"Please enter the peer''s public key: \")\n\t\t\tb := common.FromHex(s)\n\t\t\tif b == nil {\n\t\t\t\tutils.Fatalf(\"Error: can not convert hexadecimal string\")\n\t\t\t}\n\t\t\tif pub, err = crypto.UnmarshalPubkey(b); err != nil {\n\t\t\t\tutils.Fatalf(\"Error: invalid peer public key\")\n\t\t\t}\n\t\t}\n\t}\n\n\tif *requestMail {\n\t\tp2pAccept = true\n\t\tif len(msPassword) == 0 {\n\t\t\tmsPassword, err = console.Stdin.PromptPassword(\"Please enter the Mail Server password: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read Mail Server password: %s\", err)\n\t\t\t}\n\t\t}\n\t}\n\n\tif !*asymmetricMode \u0026\u0026 !*forwarderMode {\n\t\tif len(symPass) == 0 {\n\t\t\tsymPass, err = console.Stdin.PromptPassword(\"Please enter the password for symmetric encryption: \")\n\t\t\tif err != nil {\n\t\t\t\tutils.Fatalf(\"Failed to read passphrase: %v\", err)\n\t\t\t}\n\t\t}\n\n\t\tsymKeyID, err := shh.AddSymKeyFromPassword(symPass)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to create symmetric key: %s\", err)\n\t\t}\n\t\tsymKey, err = shh.GetSymKey(symKeyID)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to save symmetric key: %s\", err)\n\t\t}\n\t\tif len(*argTopic) == 0 {\n\t\t\tgenerateTopic([]byte(symPass))\n\t\t}\n\n\t\tfmt.Printf(\"Filter is configured for the topic: %x \\n\", topic)\n\t}\n\n\tif *mailServerMode {\n\t\tif len(*argDBPath) == 0 {\n\t\t\targDBPath = scanLineA(\"Please enter the path to DB file: \")\n\t\t}\n\t}\n\n\tsymFilter := whisper.Filter{\n\t\tKeySym: symKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tsymFilterID, err = shh.Subscribe(\u0026symFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n\n\tasymFilter := whisper.Filter{\n\t\tKeyAsym: asymKey,\n\t\tTopics: [][]byte{topic[:]},\n\t\tAllowP2P: p2pAccept,\n\t}\n\tasymFilterID, err = shh.Subscribe(\u0026asymFilter)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to install filter: %s\", err)\n\t}\n}\n\nfunc generateTopic(password []byte) {\n\tx := pbkdf2.Key(password, password, 4096, 128, sha512.New)\n\tfor i := 0; i \u003c len(x); i++ {\n\t\ttopic[i%whisper.TopicLength] ^= x[i]\n\t}\n}\n\nfunc waitForConnection(timeout bool) {\n\tvar cnt int\n\tvar connected bool\n\tfor !connected {\n\t\ttime.Sleep(time.Millisecond * 50)\n\t\tconnected = server.PeerCount() \u003e 0\n\t\tif timeout {\n\t\t\tcnt++\n\t\t\tif cnt \u003e 1000 {\n\t\t\t\tutils.Fatalf(\"Timeout expired, failed to connect\")\n\t\t\t}\n\t\t}\n\t}\n\n\tfmt.Println(\"Connected to peer.\")\n}\n\nfunc run() {\n\terr := startServer()\n\tif err != nil {\n\t\treturn\n\t}\n\tdefer server.Stop()\n\tshh.Start(nil)\n\tdefer shh.Stop()\n\n\tif !*forwarderMode {\n\t\tgo messageLoop()\n\t}\n\n\tif *requestMail {\n\t\trequestExpiredMessagesLoop()\n\t} else if *fileExMode {\n\t\tsendFilesLoop()\n\t} else if *fileReader {\n\t\tfileReaderLoop()\n\t} else {\n\t\tsendLoop()\n\t}\n}\n\nfunc shutdown() {\n\tclose(done)\n\tmailServer.Close()\n}\n\nfunc sendLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tsendMsg([]byte(s))\n\t\tif *asymmetricMode {\n//为方便起见，请打印您自己的消息，\n//因为在非对称模式下是不可能解密的\n\t\t\ttimestamp := time.Now().Unix()\n\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: %s\\n\", timestamp, from, s)\n\t\t}\n\t}\n}\n\nfunc sendFilesLoop() {\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\tb, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\n\t\t\th := sendMsg(b)\n\t\t\tif (h == common.Hash{}) {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: message was not sent \\n\")\n\t\t\t} else {\n\t\t\t\ttimestamp := time.Now().Unix()\n\t\t\t\tfrom := crypto.PubkeyToAddress(asymKey.PublicKey)\n\t\t\t\tfmt.Printf(\"\\n%d \u003c%x\u003e: sent message with hash %x\\n\", timestamp, from, h)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc fileReaderLoop() {\n\twatcher1 := shh.GetFilter(symFilterID)\n\twatcher2 := shh.GetFilter(asymFilterID)\n\tif watcher1 == nil \u0026\u0026 watcher2 == nil {\n\t\tfmt.Println(\"Error: neither symmetric nor asymmetric filter is installed\")\n\t\treturn\n\t}\n\n\tfor {\n\t\ts := scanLine(\"\")\n\t\tif s == quitCommand {\n\t\t\tfmt.Println(\"Quit command received\")\n\t\t\treturn\n\t\t}\n\t\traw, err := ioutil.ReadFile(s)\n\t\tif err != nil {\n\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: %s \\n\", err)\n\t\t} else {\nenv := whisper.Envelope{Data: raw} //主题为零\nmsg := env.Open(watcher1) //不管主题如何，都强制打开信封\n\t\t\tif msg == nil {\n\t\t\t\tmsg = env.Open(watcher2)\n\t\t\t}\n\t\t\tif msg == nil {\n\t\t\t\tfmt.Printf(\"\u003e\u003e\u003e Error: failed to decrypt the message \\n\")\n\t\t\t} else {\n\t\t\t\tprintMessageInfo(msg)\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunc scanLine(prompt string) string {\n\tif len(prompt) \u003e 0 {\n\t\tfmt.Print(prompt)\n\t}\n\ttxt, err := input.ReadString(''\\n'')\n\tif err != nil {\n\t\tutils.Fatalf(\"input error: %s\", err)\n\t}\n\ttxt = strings.TrimRight(txt, \"\\n\\r\")\n\treturn txt\n}\n\nfunc scanLineA(prompt string) *string {\n\ts := scanLine(prompt)\n\treturn \u0026s\n}\n\nfunc scanUint(prompt string) uint32 {\n\ts := scanLine(prompt)\n\ti, err := strconv.Atoi(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Fail to parse the lower time limit: %s\", err)\n\t}\n\treturn uint32(i)\n}\n\nfunc sendMsg(payload []byte) common.Hash {\n\tparams := whisper.MessageParams{\n\t\tSrc: asymKey,\n\t\tDst: pub,\n\t\tKeySym: symKey,\n\t\tPayload: payload,\n\t\tTopic: topic,\n\t\tTTL: uint32(*argTTL),\n\t\tPoW: *argPoW,\n\t\tWorkTime: uint32(*argWorkTime),\n\t}\n\n\tmsg, err := whisper.NewSentMessage(\u0026params)\n\tif err != nil {\n\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t}\n\n\tenvelope, err := msg.Wrap(\u0026params)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to seal message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\terr = shh.Send(envelope)\n\tif err != nil {\n\t\tfmt.Printf(\"failed to send message: %v \\n\", err)\n\t\treturn common.Hash{}\n\t}\n\n\treturn envelope.Hash()\n}\n\nfunc messageLoop() {\n\tsf := shh.GetFilter(symFilterID)\n\tif sf == nil {\n\t\tutils.Fatalf(\"symmetric filter is not installed\")\n\t}\n\n\taf := shh.GetFilter(asymFilterID)\n\tif af == nil {\n\t\tutils.Fatalf(\"asymmetric filter is not installed\")\n\t}\n\n\tticker := time.NewTicker(time.Millisecond * 50)\n\n\tfor {\n\t\tselect {\n\t\tcase \u003c-ticker.C:\n\t\t\tm1 := sf.Retrieve()\n\t\t\tm2 := af.Retrieve()\n\t\t\tmessages := append(m1, m2...)\n\t\t\tfor _, msg := range messages {\n\t\t\t\treportedOnce := false\n\t\t\t\tif !*fileExMode \u0026\u0026 len(msg.Payload) \u003c= 2048 {\n\t\t\t\t\tprintMessageInfo(msg)\n\t\t\t\t\treportedOnce = true\n\t\t\t\t}\n\n//在指定argsavedir时保存所有消息。\n//\n//如果fileexmode==true，则只显示哈希值，因为消息可能太大。\n\t\t\t\tif len(*argSaveDir) \u003e 0 {\n\t\t\t\t\twriteMessageToFile(*argSaveDir, msg, !reportedOnce)\n\t\t\t\t}\n\t\t\t}\n\t\tcase \u003c-done:\n\t\t\treturn\n\t\t}\n\t}\n}\n\nfunc printMessageInfo(msg *whisper.ReceivedMessage) {\ntimestamp := fmt.Sprintf(\"%d\", msg.Sent) //用于诊断的Unix时间戳\n\ttext := string(msg.Payload)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tif whisper.IsPubKeyEqual(msg.Src, \u0026asymKey.PublicKey) {\nfmt.Printf(\"\\n%s \u003c%x\u003e: %s\\n\", timestamp, address, text) //我的信息\n\t} else {\nfmt.Printf(\"\\n%s [%x]: %s\\n\", timestamp, address, text) //\n\t}\n}\n\nfunc writeMessageToFile(dir string, msg *whisper.ReceivedMessage, show bool) {\n\tif len(dir) == 0 {\n\t\treturn\n\t}\n\n\ttimestamp := fmt.Sprintf(\"%d\", msg.Sent)\n\tname := fmt.Sprintf(\"%x\", msg.EnvelopeHash)\n\n\tvar address common.Address\n\tif msg.Src != nil {\n\t\taddress = crypto.PubkeyToAddress(*msg.Src)\n\t}\n\n\tenv := shh.GetEnvelope(msg.EnvelopeHash)\n\tif env == nil {\n\t\tfmt.Printf(\"\\nUnexpected error: envelope not found: %x\\n\", msg.EnvelopeHash)\n\t\treturn\n\t}\n\n//这是一个示例代码；如果不想保存自己的消息，请取消注释。\n//如果whisper.ispubkeyequal（msg.src，\u0026asymkey.publickey）\n//fmt.printf（“\\n%s\u003c%x\u003e：我收到的消息，未保存：“%s''\\n”，时间戳，地址，名称）\n//返回\n//}\n\n\tfullpath := filepath.Join(dir, name)\n\terr := ioutil.WriteFile(fullpath, env.Data, 0644)\n\tif err != nil {\n\t\tfmt.Printf(\"\\n%s {%x}: message received but not saved: %s\\n\", timestamp, address, err)\n\t} else if show {\n\t\tfmt.Printf(\"\\n%s {%x}: message received and saved as ''%s'' (%d bytes)\\n\", timestamp, address, name, len(env.Data))\n\t}\n}\n\nfunc requestExpiredMessagesLoop() {\n\tvar key, peerID, bloom []byte\n\tvar timeLow, timeUpp uint32\n\tvar t string\n\tvar xt whisper.TopicType\n\n\tkeyID, err := shh.AddSymKeyFromPassword(msPassword)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to create symmetric key for mail request: %s\", err)\n\t}\n\tkey, err = shh.GetSymKey(keyID)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to save symmetric key for mail request: %s\", err)\n\t}\n\tpeerID = extractIDFromEnode(*argEnode)\n\tshh.AllowP2PMessagesFromPeer(peerID)\n\n\tfor {\n\t\ttimeLow = scanUint(\"Please enter the lower limit of the time range (unix timestamp): \")\n\t\ttimeUpp = scanUint(\"Please enter the upper limit of the time range (unix timestamp): \")\n\t\tt = scanLine(\"Enter the topic (hex). Press enter to request all messages, regardless of the topic: \")\n\t\tif len(t) == whisper.TopicLength*2 {\n\t\t\tx, err := hex.DecodeString(t)\n\t\t\tif err != nil {\n\t\t\t\tfmt.Printf(\"Failed to parse the topic: %s \\n\", err)\n\t\t\t\tcontinue\n\t\t\t}\n\t\t\txt = whisper.BytesToTopic(x)\n\t\t\tbloom = whisper.TopicToBloom(xt)\n\t\t\tobfuscateBloom(bloom)\n\t\t} else if len(t) == 0 {\n\t\t\tbloom = whisper.MakeFullNodeBloom()\n\t\t} else {\n\t\t\tfmt.Println(\"Error: topic is invalid, request aborted\")\n\t\t\tcontinue\n\t\t}\n\n\t\tif timeUpp == 0 {\n\t\t\ttimeUpp = 0xFFFFFFFF\n\t\t}\n\n\t\tdata := make([]byte, 8, 8+whisper.BloomFilterSize)\n\t\tbinary.BigEndian.PutUint32(data, timeLow)\n\t\tbinary.BigEndian.PutUint32(data[4:], timeUpp)\n\t\tdata = append(data, bloom...)\n\n\t\tvar params whisper.MessageParams\n\t\tparams.PoW = *argServerPoW\n\t\tparams.Payload = data\n\t\tparams.KeySym = key\n\t\tparams.Src = asymKey\n\t\tparams.WorkTime = 5\n\n\t\tmsg, err := whisper.NewSentMessage(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"failed to create new message: %s\", err)\n\t\t}\n\t\tenv, err := msg.Wrap(\u0026params)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Wrap failed: %s\", err)\n\t\t}\n\n\t\terr = shh.RequestHistoricMessages(peerID, env)\n\t\tif err != nil {\n\t\t\tutils.Fatalf(\"Failed to send P2P message: %s\", err)\n\t\t}\n\n\t\ttime.Sleep(time.Second * 5)\n\t}\n}\n\nfunc extractIDFromEnode(s string) []byte {\n\tn, err := discover.ParseNode(s)\n\tif err != nil {\n\t\tutils.Fatalf(\"Failed to parse enode: %s\", err)\n\t}\n\treturn n.ID[:]\n}\n\n//模糊布卢姆增加16个随机位的布卢姆\n//筛选，以便混淆包含的主题。\n//它在每个会话中都具有确定性。\n//尽管有额外的位，它将平均匹配\n//比完整节点的Bloom过滤器少32000倍的消息。\nfunc obfuscateBloom(bloom []byte) {\n\tconst half = entropySize / 2\n\tfor i := 0; i \u003c half; i++ {\n\t\tx := int(entropy[i])\n\t\tif entropy[half+i] \u003c 128 {\n\t\t\tx += 256\n\t\t}\n\nbloom[x/8] = 1 \u003c\u003c uint(x%8) //设置位号x\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":116,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/driver_x11.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_x11.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build (linux \u0026\u0026 !android) || dragonfly || openbsd\n\npackage driver\n\nimport (\n\t\"golang.org/x/exp/shiny/driver/x11driver\"\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\nfunc main(f func(screen.Screen)) {\n\tx11driver.Main(f)\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) {","lineNumber":13,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/gldriver/x11.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/x11.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build (linux \u0026\u0026 !android) || openbsd\n\npackage gldriver\n\n/*\n#cgo linux LDFLAGS: -lEGL -lGLESv2 -lX11\n#cgo openbsd LDFLAGS: -L/usr/X11R6/lib/ -lEGL -lGLESv2 -lX11\n\n#cgo openbsd CFLAGS: -I/usr/X11R6/include/\n\n#include \u003cstdbool.h\u003e\n#include \u003cstdint.h\u003e\n#include \u003cstdlib.h\u003e\n\nchar *eglGetErrorStr();\nvoid startDriver();\nvoid processEvents();\nvoid makeCurrent(uintptr_t ctx);\nvoid swapBuffers(uintptr_t ctx);\nvoid doCloseWindow(uintptr_t id);\nuintptr_t doNewWindow(int width, int height, char* title, int title_len);\nuintptr_t doShowWindow(uintptr_t id);\nuintptr_t surfaceCreate();\n*/\nimport \"C\"\nimport (\n\t\"errors\"\n\t\"runtime\"\n\t\"time\"\n\t\"unsafe\"\n\n\t\"golang.org/x/exp/shiny/driver/internal/x11key\"\n\t\"golang.org/x/exp/shiny/screen\"\n\t\"golang.org/x/mobile/event/key\"\n\t\"golang.org/x/mobile/event/mouse\"\n\t\"golang.org/x/mobile/event/paint\"\n\t\"golang.org/x/mobile/event/size\"\n\t\"golang.org/x/mobile/geom\"\n\t\"golang.org/x/mobile/gl\"\n)\n\nconst useLifecycler = true\n\nconst handleSizeEventsAtChannelReceive = true\n\nvar theKeysyms x11key.KeysymTable\n\nfunc init() {\n\t// It might not be necessary, but it probably doesn''t hurt to try to make\n\t// ''the main thread'' be ''the X11 / OpenGL thread''.\n\truntime.LockOSThread()\n}\n\nfunc newWindow(opts *screen.NewWindowOptions) (uintptr, error) {\n\twidth, height := optsSize(opts)\n\n\ttitle := opts.GetTitle()\n\tctitle := C.CString(title)\n\tdefer C.free(unsafe.Pointer(ctitle))\n\n\tretc := make(chan uintptr)\n\tuic \u003c- uiClosure{\n\t\tf: func() uintptr {\n\t\t\treturn uintptr(C.doNewWindow(C.int(width), C.int(height), ctitle, C.int(len(title))))\n\t\t},\n\t\tretc: retc,\n\t}\n\treturn \u003c-retc, nil\n}\n\nfunc initWindow(w *windowImpl) {\n\tw.glctx, w.worker = glctx, worker\n}\n\nfunc showWindow(w *windowImpl) {\n\tretc := make(chan uintptr)\n\tuic \u003c- uiClosure{\n\t\tf: func() uintptr {\n\t\t\treturn uintptr(C.doShowWindow(C.uintptr_t(w.id)))\n\t\t},\n\t\tretc: retc,\n\t}\n\tw.ctx = \u003c-retc\n\tgo drawLoop(w)\n}\n\nfunc closeWindow(id uintptr) {\n\tuic \u003c- uiClosure{\n\t\tf: func() uintptr {\n\t\t\tC.doCloseWindow(C.uintptr_t(id))\n\t\t\treturn 0\n\t\t},\n\t}\n}\n\nfunc drawLoop(w *windowImpl) {\n\tglcontextc \u003c- w.ctx.(uintptr)\n\tgo func() {\n\t\tfor range w.publish {\n\t\t\tpublishc \u003c- w\n\t\t}\n\t}()\n}\n\nvar (\n\tglcontextc = make(chan uintptr)\n\tpublishc = make(chan *windowImpl)\n\tuic = make(chan uiClosure)\n\n\t// TODO: don''t assume that there is only one window, and hence only\n\t// one (global) GL context.\n\t//\n\t// TODO: should we be able to make a shiny.Texture before having a\n\t// shiny.Window''s GL context? Should something like gl.IsProgram be a\n\t// method instead of a function, and have each shiny.Window have its own\n\t// gl.Context?\n\tglctx gl.Context\n\tworker gl.Worker\n)\n\n// uiClosure is a closure to be run on C''s UI thread.\ntype uiClosure struct {\n\tf func() uintptr\n\tretc chan uintptr\n}\n\nfunc main(f func(screen.Screen)) error {\n\tif gl.Version() == \"GL_ES_2_0\" {\n\t\treturn errors.New(\"gldriver: ES 3 required on X11\")\n\t}\n\tC.startDriver()\n\tglctx, worker = gl.NewContext()\n\n\tclosec := make(chan struct{})\n\tgo func() {\n\t\tf(theScreen)\n\t\tclose(closec)\n\t}()\n\n\t// heartbeat is a channel that, at regular intervals, directs the select\n\t// below to also consider X11 events, not just Go events (channel\n\t// communications).\n\t//\n\t// TODO: select instead of poll. Note that knowing whether to call\n\t// C.processEvents needs to select on a file descriptor, and the other\n\t// cases below select on Go channels.\n\theartbeat := time.NewTicker(time.Second / 60)\n\tworkAvailable := worker.WorkAvailable()\n\n\tfor {\n\t\tselect {\n\t\tcase \u003c-closec:\n\t\t\treturn nil\n\t\tcase ctx := \u003c-glcontextc:\n\t\t\t// TODO: do we need to synchronize with seeing a size event for\n\t\t\t// this window''s context before or after calling makeCurrent?\n\t\t\t// Otherwise, are we racing with the gl.Viewport call? I''ve\n\t\t\t// occasionally seen a stale viewport, if the window manager sets\n\t\t\t// the window width and height to something other than that\n\t\t\t// requested by XCreateWindow, but it''s not easily reproducible.\n\t\t\tC.makeCurrent(C.uintptr_t(ctx))\n\t\tcase w := \u003c-publishc:\n\t\t\tC.swapBuffers(C.uintptr_t(w.ctx.(uintptr)))\n\t\t\tw.publishDone \u003c- screen.PublishResult{}\n\t\tcase req := \u003c-uic:\n\t\t\tret := req.f()\n\t\t\tif req.retc != nil {\n\t\t\t\treq.retc \u003c- ret\n\t\t\t}\n\t\tcase \u003c-heartbeat.C:\n\t\t\tC.processEvents()\n\t\tcase \u003c-workAvailable:\n\t\t\tworker.DoWork()\n\t\t}\n\t}\n}\n\n//export onExpose\nfunc onExpose(id uintptr) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\n\tw.Send(paint.Event{External: true})\n}\n\n//export onKeysym\nfunc onKeysym(k, unshifted, shifted uint32) {\n\ttheKeysyms.Table[k][0] = unshifted\n\ttheKeysyms.Table[k][1] = shifted\n}\n\n//export onKey\nfunc onKey(id uintptr, state uint16, detail, dir uint8) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\n\tr, c := theKeysyms.Lookup(detail, state)\n\tw.Send(key.Event{\n\t\tRune: r,\n\t\tCode: c,\n\t\tModifiers: x11key.KeyModifiers(state),\n\t\tDirection: key.Direction(dir),\n\t})\n}\n\n//export onMouse\nfunc onMouse(id uintptr, x, y int32, state uint16, button, dir uint8) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\n\t// TODO: should a mouse.Event have a separate MouseModifiers field, for\n\t// which buttons are pressed during a mouse move?\n\tbtn := mouse.Button(button)\n\tswitch btn {\n\tcase 4:\n\t\tbtn = mouse.ButtonWheelUp\n\tcase 5:\n\t\tbtn = mouse.ButtonWheelDown\n\tcase 6:\n\t\tbtn = mouse.ButtonWheelLeft\n\tcase 7:\n\t\tbtn = mouse.ButtonWheelRight\n\t}\n\tif btn.IsWheel() {\n\t\tif dir != uint8(mouse.DirPress) {\n\t\t\treturn\n\t\t}\n\t\tdir = uint8(mouse.DirStep)\n\t}\n\tw.Send(mouse.Event{\n\t\tX: float32(x),\n\t\tY: float32(y),\n\t\tButton: btn,\n\t\tModifiers: x11key.KeyModifiers(state),\n\t\tDirection: mouse.Direction(dir),\n\t})\n}\n\n//export onFocus\nfunc onFocus(id uintptr, focused bool) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\n\tw.lifecycler.SetFocused(focused)\n\tw.lifecycler.SendEvent(w, w.glctx)\n}\n\n//export onConfigure\nfunc onConfigure(id uintptr, x, y, width, height, displayWidth, displayWidthMM int32) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\n\tw.lifecycler.SetVisible(x+width \u003e 0 \u0026\u0026 y+height \u003e 0)\n\tw.lifecycler.SendEvent(w, w.glctx)\n\n\tconst (\n\t\tmmPerInch = 25.4\n\t\tptPerInch = 72\n\t)\n\tpixelsPerMM := float32(displayWidth) / float32(displayWidthMM)\n\tw.Send(size.Event{\n\t\tWidthPx: int(width),\n\t\tHeightPx: int(height),\n\t\tWidthPt: geom.Pt(width),\n\t\tHeightPt: geom.Pt(height),\n\t\tPixelsPerPt: pixelsPerMM * mmPerInch / ptPerInch,\n\t})\n}\n\n//export onDeleteWindow\nfunc onDeleteWindow(id uintptr) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\n\tw.lifecycler.SetDead(true)\n\tw.lifecycler.SendEvent(w, w.glctx)\n}\n\nfunc surfaceCreate() error {\n\tif C.surfaceCreate() == 0 {\n\t\treturn errors.New(\"gldriver: surface creation failed\")\n\t}\n\treturn nil\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) error {","lineNumber":130,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/driver_darwin.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_darwin.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build darwin \u0026\u0026 !metal\n\npackage driver\n\nimport (\n\t\"golang.org/x/exp/shiny/driver/gldriver\"\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\nfunc main(f func(screen.Screen)) {\n\tgldriver.Main(f)\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) {","lineNumber":13,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/gldriver/cocoa.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/cocoa.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build darwin \u0026\u0026 !ios\n\npackage gldriver\n\n/*\n#cgo CFLAGS: -x objective-c -DGL_SILENCE_DEPRECATION\n#cgo LDFLAGS: -framework Cocoa -framework OpenGL\n#include \u003cOpenGL/gl3.h\u003e\n#import \u003cCarbon/Carbon.h\u003e // for HIToolbox/Events.h\n#import \u003cCocoa/Cocoa.h\u003e\n#include \u003cpthread.h\u003e\n#include \u003cstdint.h\u003e\n#include \u003cstdlib.h\u003e\n\nvoid startDriver();\nvoid stopDriver();\nvoid makeCurrentContext(uintptr_t ctx);\nvoid flushContext(uintptr_t ctx);\nuintptr_t doNewWindow(int width, int height, char* title);\nvoid doShowWindow(uintptr_t id);\nvoid doCloseWindow(uintptr_t id);\nuint64_t threadID();\n*/\nimport \"C\"\n\nimport (\n\t\"errors\"\n\t\"fmt\"\n\t\"log\"\n\t\"runtime\"\n\t\"unsafe\"\n\n\t\"golang.org/x/exp/shiny/driver/internal/lifecycler\"\n\t\"golang.org/x/exp/shiny/screen\"\n\t\"golang.org/x/mobile/event/key\"\n\t\"golang.org/x/mobile/event/mouse\"\n\t\"golang.org/x/mobile/event/paint\"\n\t\"golang.org/x/mobile/event/size\"\n\t\"golang.org/x/mobile/geom\"\n\t\"golang.org/x/mobile/gl\"\n)\n\nconst useLifecycler = true\n\n// TODO: change this to true, after manual testing on OS X.\nconst handleSizeEventsAtChannelReceive = false\n\nvar initThreadID C.uint64_t\n\nfunc init() {\n\t// Lock the goroutine responsible for initialization to an OS thread.\n\t// This means the goroutine running main (and calling startDriver below)\n\t// is locked to the OS thread that started the program. This is\n\t// necessary for the correct delivery of Cocoa events to the process.\n\t//\n\t// A discussion on this topic:\n\t// https://groups.google.com/forum/#!msg/golang-nuts/IiWZ2hUuLDA/SNKYYZBelsYJ\n\truntime.LockOSThread()\n\tinitThreadID = C.threadID()\n}\n\nfunc newWindow(opts *screen.NewWindowOptions) (uintptr, error) {\n\twidth, height := optsSize(opts)\n\n\ttitle := C.CString(opts.GetTitle())\n\tdefer C.free(unsafe.Pointer(title))\n\n\treturn uintptr(C.doNewWindow(C.int(width), C.int(height), title)), nil\n}\n\nfunc initWindow(w *windowImpl) {\n\tw.glctx, w.worker = gl.NewContext()\n}\n\nfunc showWindow(w *windowImpl) {\n\tC.doShowWindow(C.uintptr_t(w.id))\n}\n\n//export preparedOpenGL\nfunc preparedOpenGL(id, ctx, vba uintptr) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tw.ctx = ctx\n\tgo drawLoop(w, vba)\n}\n\nfunc closeWindow(id uintptr) {\n\tC.doCloseWindow(C.uintptr_t(id))\n}\n\nvar mainCallback func(screen.Screen)\n\nfunc main(f func(screen.Screen)) error {\n\tif tid := C.threadID(); tid != initThreadID {\n\t\tlog.Fatalf(\"gldriver.Main called on thread %d, but gldriver.init ran on %d\", tid, initThreadID)\n\t}\n\n\tmainCallback = f\n\tC.startDriver()\n\treturn nil\n}\n\n//export driverStarted\nfunc driverStarted() {\n\tgo func() {\n\t\tmainCallback(theScreen)\n\t\tC.stopDriver()\n\t}()\n}\n\n//export drawgl\nfunc drawgl(id uintptr) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn // closing window\n\t}\n\n\t// TODO: is this necessary?\n\tw.lifecycler.SetVisible(true)\n\tw.lifecycler.SendEvent(w, w.glctx)\n\n\tw.Send(paint.Event{External: true})\n\t\u003c-w.drawDone\n}\n\n// drawLoop is the primary drawing loop.\n//\n// After Cocoa has created an NSWindow and called prepareOpenGL,\n// it starts drawLoop on a locked goroutine to handle OpenGL calls.\n//\n// The screen is drawn every time a paint.Event is received, which can be\n// triggered either by the user or by Cocoa via drawgl (for example, when\n// the window is resized).\nfunc drawLoop(w *windowImpl, vba uintptr) {\n\truntime.LockOSThread()\n\tC.makeCurrentContext(C.uintptr_t(w.ctx.(uintptr)))\n\n\t// Starting in OS X 10.11 (El Capitan), the vertex array is\n\t// occasionally getting unbound when the context changes threads.\n\t//\n\t// Avoid this by binding it again.\n\tC.glBindVertexArray(C.GLuint(vba))\n\tif errno := C.glGetError(); errno != 0 {\n\t\tpanic(fmt.Sprintf(\"gldriver: glBindVertexArray failed: %d\", errno))\n\t}\n\n\tworkAvailable := w.worker.WorkAvailable()\n\n\t// TODO(crawshaw): exit this goroutine on Release.\n\tfor {\n\t\tselect {\n\t\tcase \u003c-workAvailable:\n\t\t\tw.worker.DoWork()\n\t\tcase \u003c-w.publish:\n\t\tloop:\n\t\t\tfor {\n\t\t\t\tselect {\n\t\t\t\tcase \u003c-workAvailable:\n\t\t\t\t\tw.worker.DoWork()\n\t\t\t\tdefault:\n\t\t\t\t\tbreak loop\n\t\t\t\t}\n\t\t\t}\n\t\t\tC.flushContext(C.uintptr_t(w.ctx.(uintptr)))\n\t\t\tw.publishDone \u003c- screen.PublishResult{}\n\t\t}\n\t}\n}\n\n//export setGeom\nfunc setGeom(id uintptr, ppp float32, widthPx, heightPx int) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn // closing window\n\t}\n\n\tsz := size.Event{\n\t\tWidthPx: widthPx,\n\t\tHeightPx: heightPx,\n\t\tWidthPt: geom.Pt(float32(widthPx) / ppp),\n\t\tHeightPt: geom.Pt(float32(heightPx) / ppp),\n\t\tPixelsPerPt: ppp,\n\t}\n\n\tif !handleSizeEventsAtChannelReceive {\n\t\tw.szMu.Lock()\n\t\tw.sz = sz\n\t\tw.szMu.Unlock()\n\t}\n\n\tw.Send(sz)\n}\n\n//export windowClosing\nfunc windowClosing(id uintptr) {\n\tsendLifecycle(id, (*lifecycler.State).SetDead, true)\n}\n\nfunc sendWindowEvent(id uintptr, e interface{}) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn // closing window\n\t}\n\tw.Send(e)\n}\n\nvar mods = [...]struct {\n\tflags uint32\n\tcode uint16\n\tmod key.Modifiers\n}{\n\t// Left and right variants of modifier keys have their own masks,\n\t// but they are not documented. These were determined empirically.\n\t{1\u003c\u003c17 | 0x102, C.kVK_Shift, key.ModShift},\n\t{1\u003c\u003c17 | 0x104, C.kVK_RightShift, key.ModShift},\n\t{1\u003c\u003c18 | 0x101, C.kVK_Control, key.ModControl},\n\t{33\u003c\u003c13 | 0x100, C.kVK_RightControl, key.ModControl},\n\t{1\u003c\u003c19 | 0x120, C.kVK_Option, key.ModAlt},\n\t{1\u003c\u003c19 | 0x140, C.kVK_RightOption, key.ModAlt},\n\t{1\u003c\u003c20 | 0x108, C.kVK_Command, key.ModMeta},\n\t{1\u003c\u003c20 | 0x110, 0x36 /* kVK_RightCommand */, key.ModMeta},\n}\n\nfunc cocoaMods(flags uint32) (m key.Modifiers) {\n\tfor _, mod := range mods {\n\t\tif flags\u0026mod.flags == mod.flags {\n\t\t\tm |= mod.mod\n\t\t}\n\t}\n\treturn m\n}\n\nfunc cocoaMouseDir(ty int32) mouse.Direction {\n\tswitch ty {\n\tcase C.NSLeftMouseDown, C.NSRightMouseDown, C.NSOtherMouseDown:\n\t\treturn mouse.DirPress\n\tcase C.NSLeftMouseUp, C.NSRightMouseUp, C.NSOtherMouseUp:\n\t\treturn mouse.DirRelease\n\tdefault: // dragged\n\t\treturn mouse.DirNone\n\t}\n}\n\nfunc cocoaMouseButton(button int32) mouse.Button {\n\tswitch button {\n\tcase 0:\n\t\treturn mouse.ButtonLeft\n\tcase 1:\n\t\treturn mouse.ButtonRight\n\tcase 2:\n\t\treturn mouse.ButtonMiddle\n\tdefault:\n\t\treturn mouse.ButtonNone\n\t}\n}\n\n//export mouseEvent\nfunc mouseEvent(id uintptr, x, y, dx, dy float32, ty, button int32, flags uint32) {\n\tcmButton := mouse.ButtonNone\n\tswitch ty {\n\tdefault:\n\t\tcmButton = cocoaMouseButton(button)\n\tcase C.NSMouseMoved, C.NSLeftMouseDragged, C.NSRightMouseDragged, C.NSOtherMouseDragged:\n\t\t// No-op.\n\tcase C.NSScrollWheel:\n\t\t// Note that the direction of scrolling is inverted by default\n\t\t// on OS X by the \"natural scrolling\" setting. At the Cocoa\n\t\t// level this inversion is applied to trackpads and mice behind\n\t\t// the scenes, and the value of dy goes in the direction the OS\n\t\t// wants scrolling to go.\n\t\t//\n\t\t// This means the same trackpad/mouse motion on OS X and Linux\n\t\t// can produce wheel events in opposite directions, but the\n\t\t// direction matches what other programs on the OS do.\n\t\t//\n\t\t// If we wanted to expose the physical device motion in the\n\t\t// event we could use [NSEvent isDirectionInvertedFromDevice]\n\t\t// to know if \"natural scrolling\" is enabled.\n\t\t//\n\t\t// TODO: On a trackpad, a scroll can be a drawn-out affair with a\n\t\t// distinct beginning and end. Should the intermediate events be\n\t\t// DirNone?\n\t\t//\n\t\t// TODO: handle horizontal scrolling\n\t\tbutton := mouse.ButtonWheelUp\n\t\tif dy \u003c 0 {\n\t\t\tdy = -dy\n\t\t\tbutton = mouse.ButtonWheelDown\n\t\t}\n\t\te := mouse.Event{\n\t\t\tX: x,\n\t\t\tY: y,\n\t\t\tButton: button,\n\t\t\tDirection: mouse.DirStep,\n\t\t\tModifiers: cocoaMods(flags),\n\t\t}\n\t\tfor delta := int(dy); delta != 0; delta-- {\n\t\t\tsendWindowEvent(id, e)\n\t\t}\n\t\treturn\n\t}\n\tsendWindowEvent(id, mouse.Event{\n\t\tX: x,\n\t\tY: y,\n\t\tButton: cmButton,\n\t\tDirection: cocoaMouseDir(ty),\n\t\tModifiers: cocoaMods(flags),\n\t})\n}\n\n//export keyEvent\nfunc keyEvent(id uintptr, runeVal rune, dir uint8, code uint16, flags uint32) {\n\tsendWindowEvent(id, key.Event{\n\t\tRune: cocoaRune(runeVal),\n\t\tDirection: key.Direction(dir),\n\t\tCode: cocoaKeyCode(code),\n\t\tModifiers: cocoaMods(flags),\n\t})\n}\n\n//export flagEvent\nfunc flagEvent(id uintptr, flags uint32) {\n\tfor _, mod := range mods {\n\t\tif flags\u0026mod.flags == mod.flags \u0026\u0026 lastFlags\u0026mod.flags != mod.flags {\n\t\t\tkeyEvent(id, -1, C.NSKeyDown, mod.code, flags)\n\t\t}\n\t\tif lastFlags\u0026mod.flags == mod.flags \u0026\u0026 flags\u0026mod.flags != mod.flags {\n\t\t\tkeyEvent(id, -1, C.NSKeyUp, mod.code, flags)\n\t\t}\n\t}\n\tlastFlags = flags\n}\n\nvar lastFlags uint32\n\nfunc sendLifecycle(id uintptr, setter func(*lifecycler.State, bool), val bool) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[id]\n\ttheScreen.mu.Unlock()\n\n\tif w == nil {\n\t\treturn\n\t}\n\tsetter(\u0026w.lifecycler, val)\n\tw.lifecycler.SendEvent(w, w.glctx)\n}\n\nfunc sendLifecycleAll(dead bool) {\n\twindows := []*windowImpl{}\n\n\ttheScreen.mu.Lock()\n\tfor _, w := range theScreen.windows {\n\t\twindows = append(windows, w)\n\t}\n\ttheScreen.mu.Unlock()\n\n\tfor _, w := range windows {\n\t\tw.lifecycler.SetFocused(false)\n\t\tw.lifecycler.SetVisible(false)\n\t\tif dead {\n\t\t\tw.lifecycler.SetDead(true)\n\t\t}\n\t\tw.lifecycler.SendEvent(w, w.glctx)\n\t}\n}\n\n//export lifecycleDeadAll\nfunc lifecycleDeadAll() { sendLifecycleAll(true) }\n\n//export lifecycleHideAll\nfunc lifecycleHideAll() { sendLifecycleAll(false) }\n\n//export lifecycleVisible\nfunc lifecycleVisible(id uintptr, val bool) {\n\tsendLifecycle(id, (*lifecycler.State).SetVisible, val)\n}\n\n//export lifecycleFocused\nfunc lifecycleFocused(id uintptr, val bool) {\n\tsendLifecycle(id, (*lifecycler.State).SetFocused, val)\n}\n\n// cocoaRune marks the Carbon/Cocoa private-range unicode rune representing\n// a non-unicode key event to -1, used for Rune in the key package.\n//\n// http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/CORPCHAR.TXT\nfunc cocoaRune(r rune) rune {\n\tif ''\\uE000'' \u003c= r \u0026\u0026 r \u003c= ''\\uF8FF'' {\n\t\treturn -1\n\t}\n\treturn r\n}\n\n// cocoaKeyCode converts a Carbon/Cocoa virtual key code number\n// into the standard keycodes used by the key package.\n//\n// To get a sense of the key map, see the diagram on\n//\n//\thttp://boredzo.org/blog/archives/2007-05-22/virtual-key-codes\nfunc cocoaKeyCode(vkcode uint16) key.Code {\n\tswitch vkcode {\n\tcase C.kVK_ANSI_A:\n\t\treturn key.CodeA\n\tcase C.kVK_ANSI_B:\n\t\treturn key.CodeB\n\tcase C.kVK_ANSI_C:\n\t\treturn key.CodeC\n\tcase C.kVK_ANSI_D:\n\t\treturn key.CodeD\n\tcase C.kVK_ANSI_E:\n\t\treturn key.CodeE\n\tcase C.kVK_ANSI_F:\n\t\treturn key.CodeF\n\tcase C.kVK_ANSI_G:\n\t\treturn key.CodeG\n\tcase C.kVK_ANSI_H:\n\t\treturn key.CodeH\n\tcase C.kVK_ANSI_I:\n\t\treturn key.CodeI\n\tcase C.kVK_ANSI_J:\n\t\treturn key.CodeJ\n\tcase C.kVK_ANSI_K:\n\t\treturn key.CodeK\n\tcase C.kVK_ANSI_L:\n\t\treturn key.CodeL\n\tcase C.kVK_ANSI_M:\n\t\treturn key.CodeM\n\tcase C.kVK_ANSI_N:\n\t\treturn key.CodeN\n\tcase C.kVK_ANSI_O:\n\t\treturn key.CodeO\n\tcase C.kVK_ANSI_P:\n\t\treturn key.CodeP\n\tcase C.kVK_ANSI_Q:\n\t\treturn key.CodeQ\n\tcase C.kVK_ANSI_R:\n\t\treturn key.CodeR\n\tcase C.kVK_ANSI_S:\n\t\treturn key.CodeS\n\tcase C.kVK_ANSI_T:\n\t\treturn key.CodeT\n\tcase C.kVK_ANSI_U:\n\t\treturn key.CodeU\n\tcase C.kVK_ANSI_V:\n\t\treturn key.CodeV\n\tcase C.kVK_ANSI_W:\n\t\treturn key.CodeW\n\tcase C.kVK_ANSI_X:\n\t\treturn key.CodeX\n\tcase C.kVK_ANSI_Y:\n\t\treturn key.CodeY\n\tcase C.kVK_ANSI_Z:\n\t\treturn key.CodeZ\n\tcase C.kVK_ANSI_1:\n\t\treturn key.Code1\n\tcase C.kVK_ANSI_2:\n\t\treturn key.Code2\n\tcase C.kVK_ANSI_3:\n\t\treturn key.Code3\n\tcase C.kVK_ANSI_4:\n\t\treturn key.Code4\n\tcase C.kVK_ANSI_5:\n\t\treturn key.Code5\n\tcase C.kVK_ANSI_6:\n\t\treturn key.Code6\n\tcase C.kVK_ANSI_7:\n\t\treturn key.Code7\n\tcase C.kVK_ANSI_8:\n\t\treturn key.Code8\n\tcase C.kVK_ANSI_9:\n\t\treturn key.Code9\n\tcase C.kVK_ANSI_0:\n\t\treturn key.Code0\n\t// TODO: move the rest of these codes to constants in key.go\n\t// if we are happy with them.\n\tcase C.kVK_Return:\n\t\treturn key.CodeReturnEnter\n\tcase C.kVK_Escape:\n\t\treturn key.CodeEscape\n\tcase C.kVK_Delete:\n\t\treturn key.CodeDeleteBackspace\n\tcase C.kVK_Tab:\n\t\treturn key.CodeTab\n\tcase C.kVK_Space:\n\t\treturn key.CodeSpacebar\n\tcase C.kVK_ANSI_Minus:\n\t\treturn key.CodeHyphenMinus\n\tcase C.kVK_ANSI_Equal:\n\t\treturn key.CodeEqualSign\n\tcase C.kVK_ANSI_LeftBracket:\n\t\treturn key.CodeLeftSquareBracket\n\tcase C.kVK_ANSI_RightBracket:\n\t\treturn key.CodeRightSquareBracket\n\tcase C.kVK_ANSI_Backslash:\n\t\treturn key.CodeBackslash\n\t// 50: Keyboard Non-US \"#\" and ~\n\tcase C.kVK_ANSI_Semicolon:\n\t\treturn key.CodeSemicolon\n\tcase C.kVK_ANSI_Quote:\n\t\treturn key.CodeApostrophe\n\tcase C.kVK_ANSI_Grave:\n\t\treturn key.CodeGraveAccent\n\tcase C.kVK_ANSI_Comma:\n\t\treturn key.CodeComma\n\tcase C.kVK_ANSI_Period:\n\t\treturn key.CodeFullStop\n\tcase C.kVK_ANSI_Slash:\n\t\treturn key.CodeSlash\n\tcase C.kVK_CapsLock:\n\t\treturn key.CodeCapsLock\n\tcase C.kVK_F1:\n\t\treturn key.CodeF1\n\tcase C.kVK_F2:\n\t\treturn key.CodeF2\n\tcase C.kVK_F3:\n\t\treturn key.CodeF3\n\tcase C.kVK_F4:\n\t\treturn key.CodeF4\n\tcase C.kVK_F5:\n\t\treturn key.CodeF5\n\tcase C.kVK_F6:\n\t\treturn key.CodeF6\n\tcase C.kVK_F7:\n\t\treturn key.CodeF7\n\tcase C.kVK_F8:\n\t\treturn key.CodeF8\n\tcase C.kVK_F9:\n\t\treturn key.CodeF9\n\tcase C.kVK_F10:\n\t\treturn key.CodeF10\n\tcase C.kVK_F11:\n\t\treturn key.CodeF11\n\tcase C.kVK_F12:\n\t\treturn key.CodeF12\n\t// 70: PrintScreen\n\t// 71: Scroll Lock\n\t// 72: Pause\n\t// 73: Insert\n\tcase C.kVK_Home:\n\t\treturn key.CodeHome\n\tcase C.kVK_PageUp:\n\t\treturn key.CodePageUp\n\tcase C.kVK_ForwardDelete:\n\t\treturn key.CodeDeleteForward\n\tcase C.kVK_End:\n\t\treturn key.CodeEnd\n\tcase C.kVK_PageDown:\n\t\treturn key.CodePageDown\n\tcase C.kVK_RightArrow:\n\t\treturn key.CodeRightArrow\n\tcase C.kVK_LeftArrow:\n\t\treturn key.CodeLeftArrow\n\tcase C.kVK_DownArrow:\n\t\treturn key.CodeDownArrow\n\tcase C.kVK_UpArrow:\n\t\treturn key.CodeUpArrow\n\tcase C.kVK_ANSI_KeypadClear:\n\t\treturn key.CodeKeypadNumLock\n\tcase C.kVK_ANSI_KeypadDivide:\n\t\treturn key.CodeKeypadSlash\n\tcase C.kVK_ANSI_KeypadMultiply:\n\t\treturn key.CodeKeypadAsterisk\n\tcase C.kVK_ANSI_KeypadMinus:\n\t\treturn key.CodeKeypadHyphenMinus\n\tcase C.kVK_ANSI_KeypadPlus:\n\t\treturn key.CodeKeypadPlusSign\n\tcase C.kVK_ANSI_KeypadEnter:\n\t\treturn key.CodeKeypadEnter\n\tcase C.kVK_ANSI_Keypad1:\n\t\treturn key.CodeKeypad1\n\tcase C.kVK_ANSI_Keypad2:\n\t\treturn key.CodeKeypad2\n\tcase C.kVK_ANSI_Keypad3:\n\t\treturn key.CodeKeypad3\n\tcase C.kVK_ANSI_Keypad4:\n\t\treturn key.CodeKeypad4\n\tcase C.kVK_ANSI_Keypad5:\n\t\treturn key.CodeKeypad5\n\tcase C.kVK_ANSI_Keypad6:\n\t\treturn key.CodeKeypad6\n\tcase C.kVK_ANSI_Keypad7:\n\t\treturn key.CodeKeypad7\n\tcase C.kVK_ANSI_Keypad8:\n\t\treturn key.CodeKeypad8\n\tcase C.kVK_ANSI_Keypad9:\n\t\treturn key.CodeKeypad9\n\tcase C.kVK_ANSI_Keypad0:\n\t\treturn key.CodeKeypad0\n\tcase C.kVK_ANSI_KeypadDecimal:\n\t\treturn key.CodeKeypadFullStop\n\tcase C.kVK_ANSI_KeypadEquals:\n\t\treturn key.CodeKeypadEqualSign\n\tcase C.kVK_F13:\n\t\treturn key.CodeF13\n\tcase C.kVK_F14:\n\t\treturn key.CodeF14\n\tcase C.kVK_F15:\n\t\treturn key.CodeF15\n\tcase C.kVK_F16:\n\t\treturn key.CodeF16\n\tcase C.kVK_F17:\n\t\treturn key.CodeF17\n\tcase C.kVK_F18:\n\t\treturn key.CodeF18\n\tcase C.kVK_F19:\n\t\treturn key.CodeF19\n\tcase C.kVK_F20:\n\t\treturn key.CodeF20\n\t// 116: Keyboard Execute\n\tcase C.kVK_Help:\n\t\treturn key.CodeHelp\n\t// 118: Keyboard Menu\n\t// 119: Keyboard Select\n\t// 120: Keyboard Stop\n\t// 121: Keyboard Again\n\t// 122: Keyboard Undo\n\t// 123: Keyboard Cut\n\t// 124: Keyboard Copy\n\t// 125: Keyboard Paste\n\t// 126: Keyboard Find\n\tcase C.kVK_Mute:\n\t\treturn key.CodeMute\n\tcase C.kVK_VolumeUp:\n\t\treturn key.CodeVolumeUp\n\tcase C.kVK_VolumeDown:\n\t\treturn key.CodeVolumeDown\n\t// 130: Keyboard Locking Caps Lock\n\t// 131: Keyboard Locking Num Lock\n\t// 132: Keyboard Locking Scroll Lock\n\t// 133: Keyboard Comma\n\t// 134: Keyboard Equal Sign\n\t// ...: Bunch of stuff\n\tcase C.kVK_Control:\n\t\treturn key.CodeLeftControl\n\tcase C.kVK_Shift:\n\t\treturn key.CodeLeftShift\n\tcase C.kVK_Option:\n\t\treturn key.CodeLeftAlt\n\tcase C.kVK_Command:\n\t\treturn key.CodeLeftGUI\n\tcase C.kVK_RightControl:\n\t\treturn key.CodeRightControl\n\tcase C.kVK_RightShift:\n\t\treturn key.CodeRightShift\n\tcase C.kVK_RightOption:\n\t\treturn key.CodeRightAlt\n\t// TODO key.CodeRightGUI\n\tdefault:\n\t\treturn key.CodeUnknown\n\t}\n}\n\nfunc surfaceCreate() error {\n\treturn errors.New(\"gldriver: surface creation not implemented on darwin\")\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) error {","lineNumber":98,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/gldriver/win32.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/win32.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build windows\n\npackage gldriver\n\nimport (\n\t\"errors\"\n\t\"fmt\"\n\t\"runtime\"\n\t\"syscall\"\n\t\"unsafe\"\n\n\t\"golang.org/x/exp/shiny/driver/internal/win32\"\n\t\"golang.org/x/exp/shiny/screen\"\n\t\"golang.org/x/mobile/event/key\"\n\t\"golang.org/x/mobile/event/lifecycle\"\n\t\"golang.org/x/mobile/event/mouse\"\n\t\"golang.org/x/mobile/event/paint\"\n\t\"golang.org/x/mobile/event/size\"\n\t\"golang.org/x/mobile/gl\"\n)\n\n// TODO: change this to true, after manual testing on Win32.\nconst useLifecycler = false\n\n// TODO: change this to true, after manual testing on Win32.\nconst handleSizeEventsAtChannelReceive = false\n\nfunc main(f func(screen.Screen)) error {\n\treturn win32.Main(func() { f(theScreen) })\n}\n\nvar (\n\teglGetPlatformDisplayEXT = gl.LibEGL.NewProc(\"eglGetPlatformDisplayEXT\")\n\teglInitialize = gl.LibEGL.NewProc(\"eglInitialize\")\n\teglChooseConfig = gl.LibEGL.NewProc(\"eglChooseConfig\")\n\teglGetError = gl.LibEGL.NewProc(\"eglGetError\")\n\teglBindAPI = gl.LibEGL.NewProc(\"eglBindAPI\")\n\teglCreateWindowSurface = gl.LibEGL.NewProc(\"eglCreateWindowSurface\")\n\teglCreateContext = gl.LibEGL.NewProc(\"eglCreateContext\")\n\teglMakeCurrent = gl.LibEGL.NewProc(\"eglMakeCurrent\")\n\teglSwapInterval = gl.LibEGL.NewProc(\"eglSwapInterval\")\n\teglDestroySurface = gl.LibEGL.NewProc(\"eglDestroySurface\")\n\teglSwapBuffers = gl.LibEGL.NewProc(\"eglSwapBuffers\")\n)\n\ntype eglConfig uintptr // void*\n\ntype eglInt int32\n\nvar rgb888 = [...]eglInt{\n\t_EGL_RENDERABLE_TYPE, _EGL_OPENGL_ES2_BIT,\n\t_EGL_SURFACE_TYPE, _EGL_WINDOW_BIT,\n\t_EGL_BLUE_SIZE, 8,\n\t_EGL_GREEN_SIZE, 8,\n\t_EGL_RED_SIZE, 8,\n\t_EGL_DEPTH_SIZE, 16,\n\t_EGL_STENCIL_SIZE, 8,\n\t_EGL_NONE,\n}\n\ntype ctxWin32 struct {\n\tctx uintptr\n\tdisplay uintptr // EGLDisplay\n\tsurface uintptr // EGLSurface\n}\n\nfunc newWindow(opts *screen.NewWindowOptions) (uintptr, error) {\n\tw, err := win32.NewWindow(opts)\n\tif err != nil {\n\t\treturn 0, err\n\t}\n\treturn uintptr(w), nil\n}\n\nfunc initWindow(w *windowImpl) {\n\tw.glctx, w.worker = gl.NewContext()\n}\n\nfunc showWindow(w *windowImpl) {\n\t// Show makes an initial call to sizeEvent (via win32.SizeEvent), where\n\t// we setup the EGL surface and GL context.\n\twin32.Show(syscall.Handle(w.id))\n}\n\nfunc closeWindow(id uintptr) {} // TODO\n\nfunc drawLoop(w *windowImpl) {\n\truntime.LockOSThread()\n\n\tdisplay := w.ctx.(ctxWin32).display\n\tsurface := w.ctx.(ctxWin32).surface\n\tctx := w.ctx.(ctxWin32).ctx\n\n\tif ret, _, _ := eglMakeCurrent.Call(display, surface, surface, ctx); ret == 0 {\n\t\tpanic(fmt.Sprintf(\"eglMakeCurrent failed: %v\", eglErr()))\n\t}\n\n\t// TODO(crawshaw): exit this goroutine on Release.\n\tworkAvailable := w.worker.WorkAvailable()\n\tfor {\n\t\tselect {\n\t\tcase \u003c-workAvailable:\n\t\t\tw.worker.DoWork()\n\t\tcase \u003c-w.publish:\n\t\tloop:\n\t\t\tfor {\n\t\t\t\tselect {\n\t\t\t\tcase \u003c-workAvailable:\n\t\t\t\t\tw.worker.DoWork()\n\t\t\t\tdefault:\n\t\t\t\t\tbreak loop\n\t\t\t\t}\n\t\t\t}\n\t\t\tif ret, _, _ := eglSwapBuffers.Call(display, surface); ret == 0 {\n\t\t\t\tpanic(fmt.Sprintf(\"eglSwapBuffers failed: %v\", eglErr()))\n\t\t\t}\n\t\t\tw.publishDone \u003c- screen.PublishResult{}\n\t\t}\n\t}\n}\n\nfunc init() {\n\twin32.SizeEvent = sizeEvent\n\twin32.PaintEvent = paintEvent\n\twin32.MouseEvent = mouseEvent\n\twin32.KeyEvent = keyEvent\n\twin32.LifecycleEvent = lifecycleEvent\n}\n\nfunc lifecycleEvent(hwnd syscall.Handle, to lifecycle.Stage) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[uintptr(hwnd)]\n\ttheScreen.mu.Unlock()\n\n\tif w.lifecycleStage == to {\n\t\treturn\n\t}\n\tw.Send(lifecycle.Event{\n\t\tFrom: w.lifecycleStage,\n\t\tTo: to,\n\t\tDrawContext: w.glctx,\n\t})\n\tw.lifecycleStage = to\n}\n\nfunc mouseEvent(hwnd syscall.Handle, e mouse.Event) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[uintptr(hwnd)]\n\ttheScreen.mu.Unlock()\n\n\tw.Send(e)\n}\n\nfunc keyEvent(hwnd syscall.Handle, e key.Event) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[uintptr(hwnd)]\n\ttheScreen.mu.Unlock()\n\n\tw.Send(e)\n}\n\nfunc paintEvent(hwnd syscall.Handle, e paint.Event) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[uintptr(hwnd)]\n\ttheScreen.mu.Unlock()\n\n\tif w.ctx == nil {\n\t\t// Sometimes a paint event comes in before initial\n\t\t// window size is set. Ignore it.\n\t\treturn\n\t}\n\n\t// TODO: the paint.Event should have External: true.\n\tw.Send(paint.Event{})\n}\n\nfunc sizeEvent(hwnd syscall.Handle, e size.Event) {\n\ttheScreen.mu.Lock()\n\tw := theScreen.windows[uintptr(hwnd)]\n\ttheScreen.mu.Unlock()\n\n\tif w.ctx == nil {\n\t\t// This is the initial size event on window creation.\n\t\t// Create an EGL surface and spin up a GL context.\n\t\tif err := createEGLSurface(hwnd, w); err != nil {\n\t\t\tpanic(err)\n\t\t}\n\t\tgo drawLoop(w)\n\t}\n\n\tif !handleSizeEventsAtChannelReceive {\n\t\tw.szMu.Lock()\n\t\tw.sz = e\n\t\tw.szMu.Unlock()\n\t}\n\n\tw.Send(e)\n\n\tif handleSizeEventsAtChannelReceive {\n\t\treturn\n\t}\n\n\t// Screen is dirty, generate a paint event.\n\t//\n\t// The sizeEvent function is called on the goroutine responsible for\n\t// calling the GL worker.DoWork. When compiling with -tags gldebug,\n\t// these GL calls are blocking (so we can read the error message), so\n\t// to make progress they need to happen on another goroutine.\n\tgo func() {\n\t\t// TODO: this call to Viewport is not right, but is very hard to\n\t\t// do correctly with our async events channel model. We want\n\t\t// the call to Viewport to be made the instant before the\n\t\t// paint.Event is received.\n\t\tw.glctxMu.Lock()\n\t\tw.glctx.Viewport(0, 0, e.WidthPx, e.HeightPx)\n\t\tw.glctx.ClearColor(0, 0, 0, 1)\n\t\tw.glctx.Clear(gl.COLOR_BUFFER_BIT)\n\t\tw.glctxMu.Unlock()\n\n\t\tw.Send(paint.Event{})\n\t}()\n}\n\nfunc eglErr() error {\n\tif ret, _, _ := eglGetError.Call(); ret != _EGL_SUCCESS {\n\t\treturn errors.New(eglErrString(ret))\n\t}\n\treturn nil\n}\n\nfunc createEGLSurface(hwnd syscall.Handle, w *windowImpl) error {\n\tvar displayAttribPlatforms = [][]eglInt{\n\t\t// Default\n\t\t[]eglInt{\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_DEFAULT_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MAJOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MINOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_NONE,\n\t\t},\n\t\t// Direct3D 11\n\t\t[]eglInt{\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_D3D11_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MAJOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MINOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_NONE,\n\t\t},\n\t\t// Direct3D 9\n\t\t[]eglInt{\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_D3D9_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MAJOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MINOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_NONE,\n\t\t},\n\t\t// Direct3D 11 with WARP\n\t\t// https://msdn.microsoft.com/en-us/library/windows/desktop/gg615082.aspx\n\t\t[]eglInt{\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_TYPE_D3D11_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_DEVICE_TYPE_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_DEVICE_TYPE_WARP_ANGLE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MAJOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_PLATFORM_ANGLE_MAX_VERSION_MINOR_ANGLE, _EGL_DONT_CARE,\n\t\t\t_EGL_NONE,\n\t\t},\n\t}\n\n\tdc, err := win32.GetDC(hwnd)\n\tif err != nil {\n\t\treturn fmt.Errorf(\"win32.GetDC failed: %v\", err)\n\t}\n\n\tvar display uintptr = _EGL_NO_DISPLAY\n\tfor i, displayAttrib := range displayAttribPlatforms {\n\t\tlastTry := i == len(displayAttribPlatforms)-1\n\n\t\tdisplay, _, _ = eglGetPlatformDisplayEXT.Call(\n\t\t\t_EGL_PLATFORM_ANGLE_ANGLE,\n\t\t\tuintptr(dc),\n\t\t\tuintptr(unsafe.Pointer(\u0026displayAttrib[0])),\n\t\t)\n\n\t\tif display == _EGL_NO_DISPLAY {\n\t\t\tif !lastTry {\n\t\t\t\tcontinue\n\t\t\t}\n\t\t\treturn fmt.Errorf(\"eglGetPlatformDisplayEXT failed: %v\", eglErr())\n\t\t}\n\n\t\tif ret, _, _ := eglInitialize.Call(display, 0, 0); ret == 0 {\n\t\t\tif !lastTry {\n\t\t\t\tcontinue\n\t\t\t}\n\t\t\treturn fmt.Errorf(\"eglInitialize failed: %v\", eglErr())\n\t\t}\n\t}\n\n\teglBindAPI.Call(_EGL_OPENGL_ES_API)\n\tif err := eglErr(); err != nil {\n\t\treturn err\n\t}\n\n\tvar numConfigs eglInt\n\tvar config eglConfig\n\tret, _, _ := eglChooseConfig.Call(\n\t\tdisplay,\n\t\tuintptr(unsafe.Pointer(\u0026rgb888[0])),\n\t\tuintptr(unsafe.Pointer(\u0026config)),\n\t\t1,\n\t\tuintptr(unsafe.Pointer(\u0026numConfigs)),\n\t)\n\tif ret == 0 {\n\t\treturn fmt.Errorf(\"eglChooseConfig failed: %v\", eglErr())\n\t}\n\tif numConfigs \u003c= 0 {\n\t\treturn errors.New(\"eglChooseConfig found no valid config\")\n\t}\n\n\tsurface, _, _ := eglCreateWindowSurface.Call(display, uintptr(config), uintptr(hwnd), 0, 0)\n\tif surface == _EGL_NO_SURFACE {\n\t\treturn fmt.Errorf(\"eglCreateWindowSurface failed: %v\", eglErr())\n\t}\n\n\tcontextAttribs := [...]eglInt{\n\t\t_EGL_CONTEXT_CLIENT_VERSION, 2,\n\t\t_EGL_NONE,\n\t}\n\tcontext, _, _ := eglCreateContext.Call(\n\t\tdisplay,\n\t\tuintptr(config),\n\t\t_EGL_NO_CONTEXT,\n\t\tuintptr(unsafe.Pointer(\u0026contextAttribs[0])),\n\t)\n\tif context == _EGL_NO_CONTEXT {\n\t\treturn fmt.Errorf(\"eglCreateContext failed: %v\", eglErr())\n\t}\n\n\teglSwapInterval.Call(display, 1)\n\n\tw.ctx = ctxWin32{\n\t\tctx: context,\n\t\tdisplay: display,\n\t\tsurface: surface,\n\t}\n\n\treturn nil\n}\n\nfunc surfaceCreate() error {\n\treturn errors.New(\"gldriver: surface creation not implemented on windows\")\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) error {","lineNumber":31,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/gldriver/other.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/other.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build (!darwin || ios || !cgo) \u0026\u0026 (!linux || android || !cgo) \u0026\u0026 (!openbsd || !cgo) \u0026\u0026 !windows\n\npackage gldriver\n\nimport (\n\t\"fmt\"\n\t\"runtime\"\n\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\nconst useLifecycler = true\nconst handleSizeEventsAtChannelReceive = true\n\nvar errUnsupported = fmt.Errorf(\"gldriver: unsupported GOOS/GOARCH %s/%s or cgo not enabled\", runtime.GOOS, runtime.GOARCH)\n\nfunc newWindow(opts *screen.NewWindowOptions) (uintptr, error) { return 0, errUnsupported }\n\nfunc initWindow(id *windowImpl) {}\nfunc showWindow(id *windowImpl) {}\nfunc closeWindow(id uintptr) {}\nfunc drawLoop(w *windowImpl) {}\n\nfunc surfaceCreate() error { return errUnsupported }\nfunc main(f func(screen.Screen)) error { return errUnsupported }\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) error { return errUnsupported }","lineNumber":28,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/driver_windows.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_windows.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\npackage driver\n\nimport (\n\t\"golang.org/x/exp/shiny/driver/windriver\"\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\nfunc main(f func(screen.Screen)) {\n\twindriver.Main(f)\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) {","lineNumber":11,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/aarzilli/gdlv"},"file":{"path":"vendor/golang.org/x/exp/shiny/driver/driver_fallback.go","url":"/github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_fallback.go","content":"// Copyright 2015 The Go Authors. All rights reserved.\n// Use of this source code is governed by a BSD-style\n// license that can be found in the LICENSE file.\n\n//go:build !darwin \u0026\u0026 (!linux || android) \u0026\u0026 !windows \u0026\u0026 !dragonfly \u0026\u0026 !openbsd\n\npackage driver\n\nimport (\n\t\"errors\"\n\n\t\"golang.org/x/exp/shiny/driver/internal/errscreen\"\n\t\"golang.org/x/exp/shiny/screen\"\n)\n\nfunc main(f func(screen.Screen)) {\n\tf(errscreen.Stub(errors.New(\"no driver for accessing a screen\")))\n}\n"},"lineMatches":[{"preview":"func main(f func(screen.Screen)) {","lineNumber":15,"offsetAndLengths":[[0,10]]}]}]}}}}'

295+ headers:

296+ Content-Type:

297+ - application/json

298+ status: 200 OK

299+ code: 200

300+ duration: 1.299186209s

301+- id: 5

302+ request:

303+ proto: HTTP/1.1

304+ proto_major: 1

305+ proto_minor: 1

306+ content_length: 48149

307+ host: ""

308+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_eG1GRwBeCLOUWghVcDdwhumF\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go content:\\\\\\\"func main(\\\\\\\" type:file count:10\\\",\\\"count\\\":10,\\\"timeout\\\":60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 10 matches across 10 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/yinchengtsinghua/go-ethereum-chinese/cmd/wnode/main.go\\n\\nURL: /github.com/yinchengtsinghua/go-ethereum-chinese/-/blob/cmd/wnode/main.go\\n\\n```\\n106| \\targServerPoW = flag.Float64(\\\"mspow\\\", whisper.DefaultMinimumPoW, \\\"PoW requirement for Mail Server request\\\")\\n107| \\n108| \\targIP = flag.String(\\\"ip\\\", \\\"\\\", \\\"IP address and port of this node (e.g. 127.0.0.1:30303)\\\")\\n109| \\targPub = flag.String(\\\"pub\\\", \\\"\\\", \\\"public key for asymmetric encryption\\\")\\n110| \\targDBPath = flag.String(\\\"dbpath\\\", \\\"\\\", \\\"path to the server's DB directory\\\")\\n111| \\targIDFile = flag.String(\\\"idfile\\\", \\\"\\\", \\\"file name with node id (private key)\\\")\\n112| argEnode = flag.String(\\\"boot\\\", \\\"\\\", \\\"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\\n113| \\targTopic = flag.String(\\\"topic\\\", \\\"\\\", \\\"topic in hexadecimal format (e.g. 70a4beef)\\\")\\n114| \\targSaveDir = flag.String(\\\"savedir\\\", \\\"\\\", \\\"directory where all incoming messages will be saved as files\\\")\\n115| )\\n116| func main() {\\n117| func main() {\\n118| \\tprocessArgs()\\n119| \\tinitialize()\\n120| \\trun()\\n121| \\tshutdown()\\n122| }\\n123| \\n124| func processArgs() {\\n125| \\tflag.Parse()\\n126| \\n```\\n\\n## Result 2: github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/cmd/wnode/main.go\\n\\nURL: /github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/-/blob/cmd/wnode/main.go\\n\\n```\\n106| \\targServerPoW = flag.Float64(\\\"mspow\\\", whisper.DefaultMinimumPoW, \\\"PoW requirement for Mail Server request\\\")\\n107| \\n108| \\targIP = flag.String(\\\"ip\\\", \\\"\\\", \\\"IP address and port of this node (e.g. 127.0.0.1:30303)\\\")\\n109| \\targPub = flag.String(\\\"pub\\\", \\\"\\\", \\\"public key for asymmetric encryption\\\")\\n110| \\targDBPath = flag.String(\\\"dbpath\\\", \\\"\\\", \\\"path to the server's DB directory\\\")\\n111| \\targIDFile = flag.String(\\\"idfile\\\", \\\"\\\", \\\"file name with node id (private key)\\\")\\n112| argEnode = flag.String(\\\"boot\\\", \\\"\\\", \\\"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\\n113| \\targTopic = flag.String(\\\"topic\\\", \\\"\\\", \\\"topic in hexadecimal format (e.g. 70a4beef)\\\")\\n114| \\targSaveDir = flag.String(\\\"savedir\\\", \\\"\\\", \\\"directory where all incoming messages will be saved as files\\\")\\n115| )\\n116| func main() {\\n117| func main() {\\n118| \\tprocessArgs()\\n119| \\tinitialize()\\n120| \\trun()\\n121| \\tshutdown()\\n122| }\\n123| \\n124| func processArgs() {\\n125| \\tflag.Parse()\\n126| \\n```\\n\\n## Result 3: github.com/erigontech/erigon/cmd/evm/internal/t8ntool/transition.go\\n\\nURL: /github.com/erigontech/erigon/-/blob/cmd/evm/internal/t8ntool/transition.go\\n\\n```\\n91| // compile-time conformance test\\n92| var (\\n93| \\t_ cli.ExitCoder = (*NumberedError)(nil)\\n94| )\\n95| \\n96| type input struct {\\n97| \\tAlloc types.GenesisAlloc `json:\\\"alloc,omitempty\\\"`\\n98| \\tEnv *stEnv `json:\\\"env,omitempty\\\"`\\n99| \\tTxs []*txWithKey `json:\\\"txs,omitempty\\\"`\\n100| }\\n101| func Main(ctx *cli.Context) error {\\n102| func Main(ctx *cli.Context) error {\\n103| \\tlog.Root().SetHandler(log.LvlFilterHandler(log.LvlInfo, log.StderrHandler))\\n104| \\tvar (\\n105| \\t\\terr error\\n106| \\t\\tbaseDir = \\\"\\\"\\n107| \\t)\\n108| \\tvar getTracer func(txIndex int, txHash common.Hash) (*tracing.Hooks, error)\\n109| \\n110| \\t// If user specified a basedir, make sure it exists\\n111| \\tif ctx.IsSet(OutputBasedir.Name) {\\n```\\n\\n## Result 4: github.com/cilium/hubble/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\nURL: /github.com/cilium/hubble/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\n```\\n18| \\t\\\"io/ioutil\\\"\\n19| \\t\\\"log\\\"\\n20| \\t\\\"os\\\"\\n21| \\n22| \\t\\\"google.golang.org/protobuf/proto\\\"\\n23| \\t\\\"google.golang.org/protobuf/types/known/anypb\\\"\\n24| )\\n25| \\n26| type extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\\n27| \\n28| func Main(handler extensionHandler) {\\n29| func Main(handler extensionHandler) {\\n30| \\t// unpack the request\\n31| \\tdata, err := ioutil.ReadAll(os.Stdin)\\n32| \\tif err != nil {\\n33| \\t\\tlog.Println(\\\"File error:\\\", err.Error())\\n34| \\t\\tos.Exit(1)\\n35| \\t}\\n36| \\tif len(data) == 0 {\\n37| \\t\\tlog.Println(\\\"No input data.\\\")\\n38| \\t\\tos.Exit(1)\\n```\\n\\n## Result 5: github.com/eclipse-che/che-operator/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\nURL: /github.com/eclipse-che/che-operator/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\n```\\n18| \\t\\\"io/ioutil\\\"\\n19| \\t\\\"log\\\"\\n20| \\t\\\"os\\\"\\n21| \\n22| \\t\\\"google.golang.org/protobuf/proto\\\"\\n23| \\t\\\"google.golang.org/protobuf/types/known/anypb\\\"\\n24| )\\n25| \\n26| type extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\\n27| \\n28| func Main(handler extensionHandler) {\\n29| func Main(handler extensionHandler) {\\n30| \\t// unpack the request\\n31| \\tdata, err := ioutil.ReadAll(os.Stdin)\\n32| \\tif err != nil {\\n33| \\t\\tlog.Println(\\\"File error:\\\", err.Error())\\n34| \\t\\tos.Exit(1)\\n35| \\t}\\n36| \\tif len(data) == 0 {\\n37| \\t\\tlog.Println(\\\"No input data.\\\")\\n38| \\t\\tos.Exit(1)\\n```\\n\\n## Result 6: github.com/wader/fq/pkg/cli/cli.go\\n\\nURL: /github.com/wader/fq/-/blob/pkg/cli/cli.go\\n\\n```\\n253| \\n254| func (o *stdOS) Close() error {\\n255| \\t// only close if is terminal otherwise ansi reset will write\\n256| \\t// to stdout and mess up raw output\\n257| \\tif o.rl != nil {\\n258| \\t\\to.rl.Close()\\n259| \\t}\\n260| \\tclose(o.closeChan)\\n261| \\treturn nil\\n262| }\\n263| func Main(r *interp.Registry, version string) {\\n264| func Main(r *interp.Registry, version string) {\\n265| \\tos.Exit(func() int {\\n266| \\t\\tdefer maybeProfile()()\\n267| \\t\\tmaybeLogFile()\\n268| \\n269| \\t\\tsos := newStandardOS()\\n270| \\t\\tdefer sos.Close()\\n271| \\t\\ti, err := interp.New(sos, r)\\n272| \\t\\tdefer i.Stop()\\n273| \\t\\tif err != nil {\\n```\\n\\n## Result 7: github.com/gardener/etcd-backup-restore/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\nURL: /github.com/gardener/etcd-backup-restore/-/blob/vendor/github.com/google/gnostic-models/extensions/extensions.go\\n\\n```\\n18| \\t\\\"io/ioutil\\\"\\n19| \\t\\\"log\\\"\\n20| \\t\\\"os\\\"\\n21| \\n22| \\t\\\"google.golang.org/protobuf/proto\\\"\\n23| \\t\\\"google.golang.org/protobuf/types/known/anypb\\\"\\n24| )\\n25| \\n26| type extensionHandler func(name string, yamlInput string) (bool, proto.Message, error)\\n27| \\n28| func Main(handler extensionHandler) {\\n29| func Main(handler extensionHandler) {\\n30| \\t// unpack the request\\n31| \\tdata, err := ioutil.ReadAll(os.Stdin)\\n32| \\tif err != nil {\\n33| \\t\\tlog.Println(\\\"File error:\\\", err.Error())\\n34| \\t\\tos.Exit(1)\\n35| \\t}\\n36| \\tif len(data) == 0 {\\n37| \\t\\tlog.Println(\\\"No input data.\\\")\\n38| \\t\\tos.Exit(1)\\n```\\n\\n## Result 8: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/driver.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver.go\\n\\n```\\n12| \\n13| import (\\n14| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n15| )\\n16| \\n17| // Main is called by the program's main function to run the graphical\\n18| // application.\\n19| //\\n20| // It calls f on the Screen, possibly in a separate goroutine, as some OS-\\n21| // specific libraries require being on 'the main thread'. It returns when f\\n22| func Main(f func(screen.Screen)) {\\n23| func Main(f func(screen.Screen)) {\\n24| \\tmain(f)\\n25| }\\n26| \\n```\\n\\n## Result 9: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/windriver/other.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/windriver/other.go\\n\\n```\\n12| \\n13| \\t\\\"golang.org/x/exp/shiny/driver/internal/errscreen\\\"\\n14| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n15| )\\n16| \\n17| // Main is called by the program's main function to run the graphical\\n18| // application.\\n19| //\\n20| // It calls f on the Screen, possibly in a separate goroutine, as some OS-\\n21| // specific libraries require being on 'the main thread'. It returns when f\\n22| func Main(f func(screen.Screen)) {\\n23| func Main(f func(screen.Screen)) {\\n24| \\tf(errscreen.Stub(fmt.Errorf(\\n25| \\t\\t\\\"windriver: unsupported GOOS/GOARCH %s/%s\\\", runtime.GOOS, runtime.GOARCH)))\\n26| }\\n27| \\n```\\n\\n## Result 10: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/gldriver/gldriver.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/gldriver.go\\n\\n```\\n14| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n15| \\t\\\"golang.org/x/image/math/f64\\\"\\n16| \\t\\\"golang.org/x/mobile/gl\\\"\\n17| )\\n18| \\n19| // Main is called by the program's main function to run the graphical\\n20| // application.\\n21| //\\n22| // It calls f on the Screen, possibly in a separate goroutine, as some OS-\\n23| // specific libraries require being on 'the main thread'. It returns when f\\n24| func Main(f func(screen.Screen)) {\\n25| func Main(f func(screen.Screen)) {\\n26| \\tif err := main(f); err != nil {\\n27| \\t\\tf(errscreen.Stub(err))\\n28| \\t}\\n29| }\\n30| \\n31| func mul(a, b f64.Aff3) f64.Aff3 {\\n32| \\treturn f64.Aff3{\\n33| \\t\\ta[0]*b[0] + a[1]*b[3],\\n34| \\t\\ta[0]*b[1] + a[1]*b[4],\\n```\\n\\n\",\"tool_call_id\":\"call_eG1GRwBeCLOUWghVcDdwhumF\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_zCYl929MzrVvYZ0oepRDlj2S\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go case:yes content:\\\\\\\"func main(\\\\\\\" type:file count:10\\\",\\\"count\\\":10,\\\"timeout\\\":60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 10 matches across 10 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/yinchengtsinghua/go-ethereum-chinese/cmd/wnode/main.go\\n\\nURL: /github.com/yinchengtsinghua/go-ethereum-chinese/-/blob/cmd/wnode/main.go\\n\\n```\\n106| \\targServerPoW = flag.Float64(\\\"mspow\\\", whisper.DefaultMinimumPoW, \\\"PoW requirement for Mail Server request\\\")\\n107| \\n108| \\targIP = flag.String(\\\"ip\\\", \\\"\\\", \\\"IP address and port of this node (e.g. 127.0.0.1:30303)\\\")\\n109| \\targPub = flag.String(\\\"pub\\\", \\\"\\\", \\\"public key for asymmetric encryption\\\")\\n110| \\targDBPath = flag.String(\\\"dbpath\\\", \\\"\\\", \\\"path to the server's DB directory\\\")\\n111| \\targIDFile = flag.String(\\\"idfile\\\", \\\"\\\", \\\"file name with node id (private key)\\\")\\n112| argEnode = flag.String(\\\"boot\\\", \\\"\\\", \\\"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\\n113| \\targTopic = flag.String(\\\"topic\\\", \\\"\\\", \\\"topic in hexadecimal format (e.g. 70a4beef)\\\")\\n114| \\targSaveDir = flag.String(\\\"savedir\\\", \\\"\\\", \\\"directory where all incoming messages will be saved as files\\\")\\n115| )\\n116| func main() {\\n117| func main() {\\n118| \\tprocessArgs()\\n119| \\tinitialize()\\n120| \\trun()\\n121| \\tshutdown()\\n122| }\\n123| \\n124| func processArgs() {\\n125| \\tflag.Parse()\\n126| \\n```\\n\\n## Result 2: github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/cmd/wnode/main.go\\n\\nURL: /github.com/yinchengtsinghua/golang-Eos-dpos-Ethereum/-/blob/cmd/wnode/main.go\\n\\n```\\n106| \\targServerPoW = flag.Float64(\\\"mspow\\\", whisper.DefaultMinimumPoW, \\\"PoW requirement for Mail Server request\\\")\\n107| \\n108| \\targIP = flag.String(\\\"ip\\\", \\\"\\\", \\\"IP address and port of this node (e.g. 127.0.0.1:30303)\\\")\\n109| \\targPub = flag.String(\\\"pub\\\", \\\"\\\", \\\"public key for asymmetric encryption\\\")\\n110| \\targDBPath = flag.String(\\\"dbpath\\\", \\\"\\\", \\\"path to the server's DB directory\\\")\\n111| \\targIDFile = flag.String(\\\"idfile\\\", \\\"\\\", \\\"file name with node id (private key)\\\")\\n112| argEnode = flag.String(\\\"boot\\\", \\\"\\\", \\\"bootstrap node you want to connect to (e.g. enode://E454……08D50@52.176.211.200:16428）”）\\n113| \\targTopic = flag.String(\\\"topic\\\", \\\"\\\", \\\"topic in hexadecimal format (e.g. 70a4beef)\\\")\\n114| \\targSaveDir = flag.String(\\\"savedir\\\", \\\"\\\", \\\"directory where all incoming messages will be saved as files\\\")\\n115| )\\n116| func main() {\\n117| func main() {\\n118| \\tprocessArgs()\\n119| \\tinitialize()\\n120| \\trun()\\n121| \\tshutdown()\\n122| }\\n123| \\n124| func processArgs() {\\n125| \\tflag.Parse()\\n126| \\n```\\n\\n## Result 3: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/driver_x11.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_x11.go\\n\\n```\\n3| // license that can be found in the LICENSE file.\\n4| \\n5| //go:build (linux && !android) || dragonfly || openbsd\\n6| \\n7| package driver\\n8| \\n9| import (\\n10| \\t\\\"golang.org/x/exp/shiny/driver/x11driver\\\"\\n11| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n12| )\\n13| func main(f func(screen.Screen)) {\\n14| func main(f func(screen.Screen)) {\\n15| \\tx11driver.Main(f)\\n16| }\\n17| \\n```\\n\\n## Result 4: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/gldriver/x11.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/x11.go\\n\\n```\\n120| \\t// gl.Context?\\n121| \\tglctx gl.Context\\n122| \\tworker gl.Worker\\n123| )\\n124| \\n125| // uiClosure is a closure to be run on C's UI thread.\\n126| type uiClosure struct {\\n127| \\tf func() uintptr\\n128| \\tretc chan uintptr\\n129| }\\n130| func main(f func(screen.Screen)) error {\\n131| func main(f func(screen.Screen)) error {\\n132| \\tif gl.Version() == \\\"GL_ES_2_0\\\" {\\n133| \\t\\treturn errors.New(\\\"gldriver: ES 3 required on X11\\\")\\n134| \\t}\\n135| \\tC.startDriver()\\n136| \\tglctx, worker = gl.NewContext()\\n137| \\n138| \\tclosec := make(chan struct{})\\n139| \\tgo func() {\\n140| \\t\\tf(theScreen)\\n```\\n\\n## Result 5: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/driver_darwin.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_darwin.go\\n\\n```\\n3| // license that can be found in the LICENSE file.\\n4| \\n5| //go:build darwin && !metal\\n6| \\n7| package driver\\n8| \\n9| import (\\n10| \\t\\\"golang.org/x/exp/shiny/driver/gldriver\\\"\\n11| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n12| )\\n13| func main(f func(screen.Screen)) {\\n14| func main(f func(screen.Screen)) {\\n15| \\tgldriver.Main(f)\\n16| }\\n17| \\n```\\n\\n## Result 6: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/gldriver/cocoa.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/cocoa.go\\n\\n```\\n88| \\n89| \\tw.ctx = ctx\\n90| \\tgo drawLoop(w, vba)\\n91| }\\n92| \\n93| func closeWindow(id uintptr) {\\n94| \\tC.doCloseWindow(C.uintptr_t(id))\\n95| }\\n96| \\n97| var mainCallback func(screen.Screen)\\n98| func main(f func(screen.Screen)) error {\\n99| func main(f func(screen.Screen)) error {\\n100| \\tif tid := C.threadID(); tid != initThreadID {\\n101| \\t\\tlog.Fatalf(\\\"gldriver.Main called on thread %d, but gldriver.init ran on %d\\\", tid, initThreadID)\\n102| \\t}\\n103| \\n104| \\tmainCallback = f\\n105| \\tC.startDriver()\\n106| \\treturn nil\\n107| }\\n108| \\n```\\n\\n## Result 7: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/gldriver/win32.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/win32.go\\n\\n```\\n21| \\t\\\"golang.org/x/mobile/event/paint\\\"\\n22| \\t\\\"golang.org/x/mobile/event/size\\\"\\n23| \\t\\\"golang.org/x/mobile/gl\\\"\\n24| )\\n25| \\n26| // TODO: change this to true, after manual testing on Win32.\\n27| const useLifecycler = false\\n28| \\n29| // TODO: change this to true, after manual testing on Win32.\\n30| const handleSizeEventsAtChannelReceive = false\\n31| func main(f func(screen.Screen)) error {\\n32| func main(f func(screen.Screen)) error {\\n33| \\treturn win32.Main(func() { f(theScreen) })\\n34| }\\n35| \\n36| var (\\n37| \\teglGetPlatformDisplayEXT = gl.LibEGL.NewProc(\\\"eglGetPlatformDisplayEXT\\\")\\n38| \\teglInitialize = gl.LibEGL.NewProc(\\\"eglInitialize\\\")\\n39| \\teglChooseConfig = gl.LibEGL.NewProc(\\\"eglChooseConfig\\\")\\n40| \\teglGetError = gl.LibEGL.NewProc(\\\"eglGetError\\\")\\n41| \\teglBindAPI = gl.LibEGL.NewProc(\\\"eglBindAPI\\\")\\n```\\n\\n## Result 8: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/gldriver/other.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/gldriver/other.go\\n\\n```\\n18| \\n19| var errUnsupported = fmt.Errorf(\\\"gldriver: unsupported GOOS/GOARCH %s/%s or cgo not enabled\\\", runtime.GOOS, runtime.GOARCH)\\n20| \\n21| func newWindow(opts *screen.NewWindowOptions) (uintptr, error) { return 0, errUnsupported }\\n22| \\n23| func initWindow(id *windowImpl) {}\\n24| func showWindow(id *windowImpl) {}\\n25| func closeWindow(id uintptr) {}\\n26| func drawLoop(w *windowImpl) {}\\n27| \\n28| func main(f func(screen.Screen)) error { return errUnsupported }\\n29| func main(f func(screen.Screen)) error { return errUnsupported }\\n30| \\n```\\n\\n## Result 9: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/driver_windows.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_windows.go\\n\\n```\\n1| // Copyright 2015 The Go Authors. All rights reserved.\\n2| // Use of this source code is governed by a BSD-style\\n3| // license that can be found in the LICENSE file.\\n4| \\n5| package driver\\n6| \\n7| import (\\n8| \\t\\\"golang.org/x/exp/shiny/driver/windriver\\\"\\n9| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n10| )\\n11| func main(f func(screen.Screen)) {\\n12| func main(f func(screen.Screen)) {\\n13| \\twindriver.Main(f)\\n14| }\\n15| \\n```\\n\\n## Result 10: github.com/aarzilli/gdlv/vendor/golang.org/x/exp/shiny/driver/driver_fallback.go\\n\\nURL: /github.com/aarzilli/gdlv/-/blob/vendor/golang.org/x/exp/shiny/driver/driver_fallback.go\\n\\n```\\n5| //go:build !darwin && (!linux || android) && !windows && !dragonfly && !openbsd\\n6| \\n7| package driver\\n8| \\n9| import (\\n10| \\t\\\"errors\\\"\\n11| \\n12| \\t\\\"golang.org/x/exp/shiny/driver/internal/errscreen\\\"\\n13| \\t\\\"golang.org/x/exp/shiny/screen\\\"\\n14| )\\n15| func main(f func(screen.Screen)) {\\n16| func main(f func(screen.Screen)) {\\n17| \\tf(errscreen.Stub(errors.New(\\\"no driver for accessing a screen\\\")))\\n18| }\\n19| \\n```\\n\\n\",\"tool_call_id\":\"call_zCYl929MzrVvYZ0oepRDlj2S\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

309+ headers:

310+ Accept:

311+ - application/json

312+ Content-Type:

313+ - application/json

314+ User-Agent:

315+ - OpenAI/Go 2.7.1

316+ url: https://api.openai.com/v1/chat/completions

317+ method: POST

318+ response:

319+ proto: HTTP/2.0

320+ proto_major: 2

321+ proto_minor: 0

322+ content_length: -1

323+ body: |+

324+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"TkmxdJX78D"}

324

325

325− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"X3PMgIa7BUZ"}

326+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Results"},"finish_reason":null}],"usage":null,"obfuscation":"oxkXq"}

326

327

327− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"First"},"finish_reason":null}],"usage":null,"obfuscation":"tdn8Ln7"}

328+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" limited"},"finish_reason":null}],"usage":null,"obfuscation":"eQsz"}

328

329

329− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"LBfEpXut1hO"}

330+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}],"usage":null,"obfuscation":"tBQT1JGUX"}

330

331

331− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Program"},"finish_reason":null}],"usage":null,"obfuscation":"GnkQO"}

332+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"BGj6RM3VUhE"}

332

333

333− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"MRCNPIu"}

334+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"10"},"finish_reason":null}],"usage":null,"obfuscation":"TNt1XG8F3w"}

334

335

335− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"QvR1QEB66"}

336+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"5UibFA8WUnP"}

336

337

337− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"weRuYKKOF0g"}

338+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" Example"},"finish_reason":null}],"usage":null,"obfuscation":"tWgI"}

338

339

339− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"6rEMg"}

340+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" query"},"finish_reason":null}],"usage":null,"obfuscation":"5TiXvP"}

340

341

341− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"ZrCEW3Z0"}

342+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":\n"},"finish_reason":null}],"usage":null,"obfuscation":"YaCg9cNQt"}

342

343

343− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/g"},"finish_reason":null}],"usage":null,"obfuscation":"5eDRgu6Qk2"}

344+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"lang"},"finish_reason":null}],"usage":null,"obfuscation":"PtJadCBC"}

344

345

345− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}],"usage":null,"obfuscation":"nGUWe3e"}

346+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"D9B8G37iv0C"}

346

347

347− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/app"},"finish_reason":null}],"usage":null,"obfuscation":"AmbXaeag"}

348+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"VvbIGDdzYn"}

348

349

349− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"engine"},"finish_reason":null}],"usage":null,"obfuscation":"60wX0x"}

350+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" case"},"finish_reason":null}],"usage":null,"obfuscation":"kquKzeW"}

350

351

351− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/c"},"finish_reason":null}],"usage":null,"obfuscation":"VXaNnDqu8l"}

352+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"odirr68aGrP"}

352

353

353− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"md"},"finish_reason":null}],"usage":null,"obfuscation":"15eQlPOmSb"}

354+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"yes"},"finish_reason":null}],"usage":null,"obfuscation":"X2zWw31Pc"}

354

355

355− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/a"},"finish_reason":null}],"usage":null,"obfuscation":"cf54QE8d4V"}

356+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" content"},"finish_reason":null}],"usage":null,"obfuscation":"v0dH"}

356

357

357− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"eb"},"finish_reason":null}],"usage":null,"obfuscation":"XYO47vUhxF"}

358+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":\""},"finish_reason":null}],"usage":null,"obfuscation":"LSKrXsMRV"}

358

359

359− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"und"},"finish_reason":null}],"usage":null,"obfuscation":"ZBQGlnE04"}

360+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}],"usage":null,"obfuscation":"7yqmuJKn"}

360

361

361− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ler"},"finish_reason":null}],"usage":null,"obfuscation":"hcGXZtpCy"}

362+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"fBdjQyD"}

362

363

363− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/a"},"finish_reason":null}],"usage":null,"obfuscation":"b1GTAHfQn9"}

364+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"(\""},"finish_reason":null}],"usage":null,"obfuscation":"G6n0iTT4J"}

364

365

365− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"eb"},"finish_reason":null}],"usage":null,"obfuscation":"9L7C479bnY"}

366+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" type"},"finish_reason":null}],"usage":null,"obfuscation":"VVGSc4C"}

366

367

367− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"und"},"finish_reason":null}],"usage":null,"obfuscation":"X7Z3gkOCt"}

368+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":file"},"finish_reason":null}],"usage":null,"obfuscation":"Z1LZDtj"}

368

369

369− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ler"},"finish_reason":null}],"usage":null,"obfuscation":"bImvdbjjh"}

370+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" count"},"finish_reason":null}],"usage":null,"obfuscation":"tyhw8f"}

370

371

371− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"zzCkp9X94"}

372+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"IHZW3jdt7U6"}

372

373

373− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"lhyhbQ4JfPs"}

374+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"10"},"finish_reason":null}],"usage":null,"obfuscation":"IyZ7VLwPNT"}

374

375

375− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"AHlRht"}

376+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"I6McGs"}

376

377

377− data: {"id":"chatcmpl-CQ4K0qFoR8vXPTdl2hDwEGIrpfAD3","object":"chat.completion.chunk","created":1760329176,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7312,"completion_tokens":869,"total_tokens":8181,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":768,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"n"}

378+ data: {"id":"chatcmpl-CTnvunTecuCMr1iu4GnvlBVJ9MMMg","object":"chat.completion.chunk","created":1761219490,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":11883,"completion_tokens":28,"total_tokens":11911,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ep1wm"}

378

379

379 data: [DONE]

380 data: [DONE]

380

381

@@ -383,4 +384,4 @@ interactions:

383 - text/event-stream; charset=utf-8

384 - text/event-stream; charset=utf-8

384 status: 200 OK

385 status: 200 OK

385 code: 200

386 code: 200

386− duration: 11.871188417s

387+ duration: 1.63876275s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/update_a_file.yaml+251−194

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,31 +24,25 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"6s2EGgvG7pJgIF"}

27+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OxhGdRyp1mnS8O"}

29− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Update"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9ZrflYTwGO"}

29+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Changing"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"tz7olzIb"}

31− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"yJScQMfGgph"}

31+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Print"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"tpb5c272wb"}

33− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8MLQ7WuxnRsVO"}

33+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Statement"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"BrDALU"}

35− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0QVYy6QeCXHnH"}

35+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"uEzS3Is70f6Ie"}

37− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Print"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7faLDwrKJz"}

37+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Custom"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ypWrTgtTw"}

39− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" \""},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pgtE6s791r04J"}

39+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Welcome"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HGkfX91N"}

41− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rj303joO5ch"}

41+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Message"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ZNehWbUD"}

43− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" from"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1MRlnKdkfZ8"}

43+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Tf0CjWsQfA"}

45− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Crush"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Dx79nM3uDa"}

45+ data: {"id":"chatcmpl-CTnsl7uyIEQLnKLCeVcwJzV5O51fJ","object":"chat.completion.chunk","created":1761219295,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":7,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"TTbGOFvAcCt4us"}

46−

47− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"\""},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IzsD4gA0cYsBHp"}

48−

49− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"q1KLYQX7ZN"}

50−

51− data: {"id":"chatcmpl-CQ4Hgzo3VYMs8Kyhu29ceXBTBABlj","object":"chat.completion.chunk","created":1760329032,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":10,"total_tokens":149,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"LzZ7G56PhpZMn"}

53 data: [DONE]

47 data: [DONE]

@@ -57,22 +51,22 @@ interactions:

57 - text/event-stream; charset=utf-8

51 - text/event-stream; charset=utf-8

58 status: 200 OK

52 status: 200 OK

59 code: 200

53 code: 200

60− duration: 981.594041ms

54+ duration: 582.088292ms

61- id: 1

55- id: 1

62 request:

56 request:

63 proto: HTTP/1.1

57 proto: HTTP/1.1

64 proto_major: 1

58 proto_major: 1

65 proto_minor: 1

59 proto_minor: 1

66− content_length: 30727

60+ content_length: 29883

67 host: ""

61 host: ""

68− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

62+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

69 headers:

63 headers:

70 Accept:

64 Accept:

71 - application/json

65 - application/json

72 Content-Type:

66 Content-Type:

73 - application/json

67 - application/json

74 User-Agent:

68 User-Agent:

75− - OpenAI/Go 2.3.0

69+ - OpenAI/Go 2.7.1

76 url: https://api.openai.com/v1/chat/completions

70 url: https://api.openai.com/v1/chat/completions

77 method: POST

71 method: POST

78 response:

72 response:

@@ -81,65 +75,116 @@ interactions:

81 proto_minor: 0

75 proto_minor: 0

82 content_length: -1

76 content_length: -1

83 body: |+

77 body: |+

84− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Y2LAQF2yCXyV5XuHGMiRiXUs","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"vmvbbhSTgIGqbY"}

78+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_Wa8nxiYWCcBFQAvMGsGLmHCl","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"F2QVWyRIzw3spS"}

79+

80+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"JDjYSg59ZqVs9qB"}

86− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mOSbmXlo1Kqg2Y5"}

82+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9qDa0ySDr9KeqC"}

88− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wZMNARXgBeg25v"}

84+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iQSAtIo3elo1n8M"}

90− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HNu574xuTcLA40k"}

86+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \".\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"M429lBy3TSA"}

92− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pKeh9vFisLaiqb"}

88+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"jxXwLWs68pIMjXM"}

94− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VFXR9mR8Dua7Uph"}

90+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yYkao7LEpijCo"}

96− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hUdV4kJHfQmEOjn"}

92+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"83aoBFbbW8jg6Sp"}

98− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bKOzsLf1uLNvbd3"}

94+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"7"}

100− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HcfHzpycSDEpX"}

96+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"}

101

102− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3Ac7vNcGq6BQl"}

98+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"}

103

104− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LqUGGtaGN0oHP"}

100+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

105

101

106− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zXP7Gb1bMxSIT"}

102+ data: {"id":"chatcmpl-CTnslhfilo1RcT5OuYdzEX3Loz3VA","object":"chat.completion.chunk","created":1761219295,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6476,"completion_tokens":220,"total_tokens":6696,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Q"}

103+

104+ data: [DONE]

105+

106+ headers:

107+ Content-Type:

108+ - text/event-stream; charset=utf-8

109+ status: 200 OK

110+ code: 200

111+ duration: 5.289429917s

112+- id: 2

113+ request:

114+ proto: HTTP/1.1

115+ proto_major: 1

116+ proto_minor: 1

117+ content_length: 30212

118+ host: ""

119+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

120+ headers:

121+ Accept:

122+ - application/json

123+ Content-Type:

124+ - application/json

125+ User-Agent:

126+ - OpenAI/Go 2.7.1

127+ url: https://api.openai.com/v1/chat/completions

128+ method: POST

129+ response:

130+ proto: HTTP/2.0

131+ proto_major: 2

132+ proto_minor: 0

133+ content_length: -1

134+ body: |+

135+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_ArFVi3JY4UWeYQo1nG9l2UHy","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"pF3rt2oVW4K8"}

107

136

108− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tynHNxGUsYgIs"}

137+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"vDa1LXJqumwZSqp"}

109

138

110− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

139+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CSnxZmi04NKwO3"}

111

140

112− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

141+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f9UN93GpT3kET"}

113

142

114− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

143+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xz7UBaWuMGedNNz"}

115

144

116− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"}

145+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cIU79NXivTvGMDd"}

117

146

118− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6"}

147+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gZ01pK3mKLROISZ"}

119

148

120− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tk3CdMxXPEE"}

149+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QLabdJ7gD0V2GO9"}

121

150

122− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

151+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0V5zpt5ifWeaJg6"}

123

152

124− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GwMELtqcKBaN2"}

153+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VSxOggFZaypNm"}

125

154

126− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"OM3nh53hSCNXMhD"}

155+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8tU7cWUrNv5kj"}

127

156

128− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Uxl6PIgfmDDsMBc"}

157+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bj8Y3ADP0maO1"}

129

158

130− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z6zjsbkxX8OkR"}

159+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SzhJZydgE6sVR"}

131

160

132− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j70kck9ZkAR1UqF"}

161+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3t92ECGBQuCBs"}

133

162

134− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"U"}

163+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

135

164

136− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"}

165+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

137

166

138− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"O"}

167+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

139

168

140− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

169+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"u"}

141

170

142− data: {"id":"chatcmpl-CQ4HfpysV833b72y6Rh0TVhVgPSEZ","object":"chat.completion.chunk","created":1760329031,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6575,"completion_tokens":237,"total_tokens":6812,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"2"}

171+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"}

172+

173+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BbRDgt9zYtM"}

174+

175+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

176+

177+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8v0SvBOWz3O91"}

178+

179+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FO7NhOEG9A1DQ"}

180+

181+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z7Y6syEmUjTerH9"}

182+

183+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EF7X03u8vHCj7ws"}

184+

185+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

186+

187+ data: {"id":"chatcmpl-CTnsqGFaJSRAmlEw3HiIwSIa1F4yL","object":"chat.completion.chunk","created":1761219300,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6537,"completion_tokens":35,"total_tokens":6572,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"D7oZ"}

143

188

144 data: [DONE]

189 data: [DONE]

145

190

@@ -148,22 +193,22 @@ interactions:

148 - text/event-stream; charset=utf-8

193 - text/event-stream; charset=utf-8

149 status: 200 OK

194 status: 200 OK

150 code: 200

195 code: 200

151− duration: 6.124215583s

196+ duration: 2.044222375s

152−- id: 2

197+- id: 3

153 request:

198 request:

154 proto: HTTP/1.1

199 proto: HTTP/1.1

155 proto_major: 1

200 proto_major: 1

156 proto_minor: 1

201 proto_minor: 1

157− content_length: 31112

202+ content_length: 30660

158 host: ""

203 host: ""

159− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

204+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

160 headers:

205 headers:

161 Accept:

206 Accept:

162 - application/json

207 - application/json

163 Content-Type:

208 Content-Type:

164 - application/json

209 - application/json

165 User-Agent:

210 User-Agent:

166− - OpenAI/Go 2.3.0

211+ - OpenAI/Go 2.7.1

167 url: https://api.openai.com/v1/chat/completions

212 url: https://api.openai.com/v1/chat/completions

168 method: POST

213 method: POST

169 response:

214 response:

@@ -172,59 +217,59 @@ interactions:

172 proto_minor: 0

217 proto_minor: 0

173 content_length: -1

218 content_length: -1

174 body: |+

219 body: |+

175− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_wV7rNKeXv57wTn41fY8P4E2R","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"IU8gqAMeOVUh"}

220+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_lH6mbJbFqv4bAiHRAuifJsTp","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"5htQNoYIICHL"}

176

221

177− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mW3syIqGgzxHjnK"}

222+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZhESW6QMj8HBAxK"}

178

223

179− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z0PvsdLYNfuAye"}

224+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kRViH08UgnVFrU"}

180

225

181− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L3VuakhTPrG3l"}

226+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KWh5aHSBwivPe"}

182

227

183− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hqnJGSpIE7ZLT9b"}

228+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FanrHVsvtjiynGg"}

184

229

185− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cseKSTQnKTiQ4ZS"}

230+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K6S5Ytc5Fz7zDJs"}

186

231

187− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ARK34rKsDg161T6"}

232+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dpQfBEvr40CnYat"}

188

233

189− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qBOxLCqgNIVX92c"}

234+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qnvD39qvYbu34qU"}

190

235

191− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OGRBjjcVyT1whBh"}

236+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"E0Q7iWBpsIFdyFi"}

192

237

193− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DDD8Gbz7Tnpxd"}

238+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qyf4EA1fIIIwt"}

194

239

195− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QDwfnKlzxZ9g8"}

240+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ntyzPq0ktRzpD"}

196

241

197− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o1X8PTQNddDf8"}

242+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7MtqAI9SMzZzF"}

198

243

199− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NfTrmlnujBczW"}

244+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3lNRQiSlEyfhY"}

200

245

201− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n8braSRg9bwW1"}

246+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MNTqkIlyGPRgT"}

202

247

203− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

248+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

204

249

205− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

250+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

206

251

207− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

252+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

208

253

209− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"}

254+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"}

210

255

211− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j"}

256+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"}

212

257

213− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EvYKBYoKaIc"}

258+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eNrTSmuw3yT"}

214

259

215− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

260+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

216

261

217− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nslUTRgbwHwgP"}

262+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5gWfvDgHdOiAz"}

218

263

219− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1IDtSe47yjKMt"}

264+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CF7KA4nhjJBaQTR"}

220

265

221− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RJdMcrIkChMAhPn"}

266+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SZ9kfoVw5ez6Pc"}

222

267

223− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DWlHetQa82PQY0j"}

268+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LsxlmxaM52AXrVt"}

224

269

225− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

270+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

226

271

227− data: {"id":"chatcmpl-CQ4HnR32ZP6HmJanH9aHSSmEdG3nC","object":"chat.completion.chunk","created":1760329039,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6652,"completion_tokens":35,"total_tokens":6687,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"I1sJ"}

272+ data: {"id":"chatcmpl-CTnssP5Sj10LNExmFiln4AyzC62Il","object":"chat.completion.chunk","created":1761219302,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6634,"completion_tokens":361,"total_tokens":6995,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"N"}

228

273

229 data: [DONE]

274 data: [DONE]

230

275

@@ -233,22 +278,22 @@ interactions:

233 - text/event-stream; charset=utf-8

278 - text/event-stream; charset=utf-8

234 status: 200 OK

279 status: 200 OK

235 code: 200

280 code: 200

236− duration: 2.175440959s

281+ duration: 6.583581541s

237−- id: 3

282+- id: 4

238 request:

283 request:

239 proto: HTTP/1.1

284 proto: HTTP/1.1

240 proto_major: 1

285 proto_major: 1

241 proto_minor: 1

286 proto_minor: 1

242− content_length: 31560

287+ content_length: 31036

243 host: ""

288 host: ""

244− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_wV7rNKeXv57wTn41fY8P4E2R\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_wV7rNKeXv57wTn41fY8P4E2R\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

289+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_lH6mbJbFqv4bAiHRAuifJsTp\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_lH6mbJbFqv4bAiHRAuifJsTp\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

245 headers:

290 headers:

246 Accept:

291 Accept:

247 - application/json

292 - application/json

248 Content-Type:

293 Content-Type:

249 - application/json

294 - application/json

250 User-Agent:

295 User-Agent:

251− - OpenAI/Go 2.3.0

296+ - OpenAI/Go 2.7.1

252 url: https://api.openai.com/v1/chat/completions

297 url: https://api.openai.com/v1/chat/completions

253 method: POST

298 method: POST

254 response:

299 response:

@@ -257,123 +302,113 @@ interactions:

257 proto_minor: 0

302 proto_minor: 0

258 content_length: -1

303 content_length: -1

259 body: |+

304 body: |+

260− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_EYqplDdiLJqBKLszhf1zFXff","type":"function","function":{"name":"edit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"k351gWox4A0N"}

305+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_o0u65HA4wQDn0xJQCE31VJc2","type":"function","function":{"name":"edit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"zJ7aPD1QkvLp"}

261−

262− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lONEt5c853Vs7uG"}

263−

264− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5ezkjvMkwCdETR"}

265−

266− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XTfZ1KpJFIjfq"}

267−

268− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9YVi715ECAgVLUz"}

269

306

270− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0ZbKHQfwY5O3aQb"}

307+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"OqdzVF6ecjT1JD9"}

271

308

272− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zMk3anMSwTyU33u"}

309+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lg6vcw2t0zl66G"}

273

310

274− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JBGePskbthv8Wv0"}

311+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kZAUUrHJZiOCA"}

275

312

276− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qU99IEyxP1HTQB0"}

313+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"32I9zhJwuIAGKiw"}

277

314

278− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xUowoOdj3bwrE"}

315+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kO2qGvORa5T3c82"}

279

316

280− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hyGKbTAYETf3z"}

317+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0vmu65cuNfWqKMS"}

281

318

282− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lU5GRLJFt9DEc"}

319+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SNVZlCeTUvoQztG"}

283

320

284− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X2QXQE0rZCrgv"}

321+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e42WM5RLanJVtuN"}

285

322

286− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6pGNj7UK0GThO"}

323+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"unscqepNGjzHG"}

287

324

288− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

325+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xZhHSDr7qUOmm"}

289

326

290− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

327+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zWJ76GvTFS7nY"}

291

328

292− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

329+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jFROflY4HvWNJ"}

293

330

294− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"}

331+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KvnoBiAkmmco0"}

295

332

296− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y"}

333+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

297

334

298− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"97M6eZ458Uk"}

335+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

299

336

300− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

337+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

301

338

302− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OcXiOI6CrpU3s"}

339+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H"}

303

340

304− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0b1cpwCJfHwx2"}

341+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V"}

305

342

306− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zd2DksT2EDb7SOT"}

343+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ataaPpURIhn"}

307

344

308− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PmBSDOxbFLkRw"}

345+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

309

346

310− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"re1CPOi9B31KX4X"}

347+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Oxp9sB7DhELV1"}

311

348

312− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8D0b5ZKaJnm"}

349+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cCM4TPwUFMB01"}

313

350

314− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZbM6VNw57uVVt"}

351+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FzWxEZE5GWrhWff"}

315

352

316− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

353+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"0aiNm3YZs2aAo"}

317

354

318− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

355+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P6WIyd6oXUbDBG3"}

319

356

320− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

357+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"anjgmRb9AN4"}

321

358

322− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XefCQD48M7"}

359+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tWbjR1vYsHNH1"}

323

360

324− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"4ymqYVMprQfIv"}

361+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

325

362

326− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kPa5MTKyL7lgs"}

363+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

327

364

328− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"U"}

365+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

329

366

330− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ut3HQKt1kLgN"}

367+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KV9QQkeUFB"}

331

368

332− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0oulBLMrSJ9ecwd"}

369+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"kRy6O4jzNvh3O"}

333

370

334− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SlTJp21jhSg166a"}

371+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wk90LeuKQzDgc"}

335

372

336− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"NacJmtVtlOX2I"}

373+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"x"}

337

374

338− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6hZ6Ezh2yGOBejN"}

375+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AoxuCuy6aPns"}

339

376

340− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AMhHCv7dEd2"}

377+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3KSMm3iIyNGDLKJ"}

341

378

342− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"DAdhz5k4yEoUw"}

379+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HajTsrENY6mO4mh"}

343

380

344− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

381+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ayyc9BEYwftLf"}

345

382

346− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

383+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6SUrtoXtnTPYlMF"}

347

384

348− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

385+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gXhT0FhiBDX"}

349

386

350− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"my0hcr4Oq1"}

387+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"rTrvFTqmTAlLs"}

351

388

352− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"YyMVtUMWzlsO5"}

389+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

353

390

354− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y9YzUfvUdBWeW"}

391+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

355

392

356− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" from"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eTVK5ZuAu1cHj"}

393+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

357

394

358− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fB3OG4wH8Knr"}

395+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ADhuu9iJ9U"}

359

396

360− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RPwzHny8EqAvo"}

397+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"U9Fxs8kpZDBld"}

361

398

362− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"blOaBHuWx0hDj"}

399+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s2MP5X1HwC9ei"}

363

400

364− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"replace"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q7GWYYlFtAD"}

401+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" from"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lqUOD7yw61PoY"}

365

402

366− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_all"}}]},"finish_reason":null}],"usage":null,"obfuscation":"piNAx9luZppfg5"}

403+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0zWcU7BkkHuB"}

367

404

368− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Oe9MlLktba6fSZu"}

405+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KzQmhGhgxCjNF"}

369

406

370− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"false"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RcTA8EEHCjqIl"}

407+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OMX8ybM52TwKCo0"}

371

408

372− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8"}

409+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

373

410

374− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

411+ data: {"id":"chatcmpl-CTnsz9oD63oBwvtv5cRPqsLxAvdDK","object":"chat.completion.chunk","created":1761219309,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6709,"completion_tokens":644,"total_tokens":7353,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"n"}

375−

376− data: {"id":"chatcmpl-CQ4Ho1tc46EkQak5bq6MQfK7IAVSe","object":"chat.completion.chunk","created":1760329040,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6749,"completion_tokens":649,"total_tokens":7398,"prompt_tokens_details":{"cached_tokens":6656,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"O"}

377

412

378 data: [DONE]

413 data: [DONE]

379

414

@@ -382,22 +417,22 @@ interactions:

382 - text/event-stream; charset=utf-8

417 - text/event-stream; charset=utf-8

383 status: 200 OK

418 status: 200 OK

384 code: 200

419 code: 200

385− duration: 10.942074s

420+ duration: 9.547513917s

386−- id: 4

421+- id: 5

387 request:

422 request:

388 proto: HTTP/1.1

423 proto: HTTP/1.1

389 proto_major: 1

424 proto_major: 1

390 proto_minor: 1

425 proto_minor: 1

391− content_length: 32109

426+ content_length: 31563

392 host: ""

427 host: ""

393− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_wV7rNKeXv57wTn41fY8P4E2R\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_wV7rNKeXv57wTn41fY8P4E2R\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_EYqplDdiLJqBKLszhf1zFXff\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\",\\\"replace_all\\\":false}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_EYqplDdiLJqBKLszhf1zFXff\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

428+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_lH6mbJbFqv4bAiHRAuifJsTp\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_lH6mbJbFqv4bAiHRAuifJsTp\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_o0u65HA4wQDn0xJQCE31VJc2\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_o0u65HA4wQDn0xJQCE31VJc2\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

394 headers:

429 headers:

395 Accept:

430 Accept:

396 - application/json

431 - application/json

397 Content-Type:

432 Content-Type:

398 - application/json

433 - application/json

399 User-Agent:

434 User-Agent:

400− - OpenAI/Go 2.3.0

435+ - OpenAI/Go 2.7.1

401 url: https://api.openai.com/v1/chat/completions

436 url: https://api.openai.com/v1/chat/completions

402 method: POST

437 method: POST

403 response:

438 response:

@@ -406,59 +441,81 @@ interactions:

406 proto_minor: 0

441 proto_minor: 0

407 content_length: -1

442 content_length: -1

408 body: |+

443 body: |+

409− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_W5U3KN6Bu45HQ3xHaxcvzlDu","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"qsgR1AXCWcLS"}

444+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_gRff8NsecYHFsCOKKmUYNcuS","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"prnI65B4XFqZ"}

445+

446+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"DYohnFnZv58BlGD"}

447+

448+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IyeMjL8ke6c"}

449+

450+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"GSOQVKiVwCk6R"}

451+

452+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

453+

454+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VtOFdNv8EJh6dh"}

410

455

411− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"qKlyQyvz2NMmuzR"}

456+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

412

457

413− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"a3NiOkDkXq4c07"}

458+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uEepOXAoT4Qjst6"}

414

459

415− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WtHsxwqPP8295"}

460+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"grQNO6rLNrziilI"}

416

461

417− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OZR4oiP50Z3FJe9"}

462+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VyCUxsbuiQFfoxs"}

418

463

419− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RePA1IqQoAWSLs1"}

464+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z1zQVisZvUhXU"}

420

465

421− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RFaSEnMyPubntdC"}

466+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8IuEnv4jcUQPb"}

422

467

423− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HXovMpqSH8vVfvG"}

468+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yZP2NqYGIsK5N"}

424

469

425− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NDxB6EyK6TnP9UK"}

470+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cTupb3wKutzrb"}

426

471

427− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0VCsSI1ov60Vj"}

472+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eia67fGsS9THM"}

428

473

429− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yXrSLksz9gJIj"}

474+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

430

475

431− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BRKYWEwSDoEpM"}

476+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

432

477

433− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aWClD5zwcuV9V"}

478+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

434

479

435− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VYNRHW66HORWh"}

480+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"}

436

481

437− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

482+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G"}

438

483

439− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

484+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jCbvrKjLyUA"}

440

485

441− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

486+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

442

487

443− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s"}

488+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f2Z4OIUDXSwPk"}

444

489

445− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"}

490+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7QYXWGEnl6IET"}

446

491

447− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pe9qsxHEmss"}

492+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2mD3tLhs9ARfCXd"}

448

493

449− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

494+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"u7qJqqWIYpc7N"}

450

495

451− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PqYT4gnYfDAxe"}

496+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"u22e3Bj"}

452

497

453− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3gFaMsknoZjwQ"}

498+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tl51zfmHVcgB5"}

454

499

455− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JAceGg1rBSAdPGG"}

500+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qNGF0epT5fhUB21"}

456

501

457− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"srsD1PUl8H9GCWu"}

502+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hs12ur7WVCSHvk"}

458

503

459− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

504+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C5VK2k4zGZOmvXv"}

460

505

461− data: {"id":"chatcmpl-CQ4HzynjmcveYZg3qhw17Q3D44H3X","object":"chat.completion.chunk","created":1760329051,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6857,"completion_tokens":35,"total_tokens":6892,"prompt_tokens_details":{"cached_tokens":6656,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"oIb4"}

506+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" program"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xikSK4QVSl"}

507+

508+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" to"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OFsWRO9aP4mqZfL"}

509+

510+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OzHQvSsarrAN7"}

511+

512+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" output"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7s1E7hhwwuN"}

513+

514+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ndaEO6q0V0VrcS6"}

515+

516+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

517+

518+ data: {"id":"chatcmpl-CTnt9rBZWrdIMn7IujVVj3d7Ul7EA","object":"chat.completion.chunk","created":1761219319,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6812,"completion_tokens":47,"total_tokens":6859,"prompt_tokens_details":{"cached_tokens":6656,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Xubk"}

462

519

463 data: [DONE]

520 data: [DONE]

464

521

@@ -467,22 +524,22 @@ interactions:

467 - text/event-stream; charset=utf-8

524 - text/event-stream; charset=utf-8

468 status: 200 OK

525 status: 200 OK

469 code: 200

526 code: 200

470− duration: 3.002568875s

527+ duration: 1.214903708s

471−- id: 5

528+- id: 6

472 request:

529 request:

473 proto: HTTP/1.1

530 proto: HTTP/1.1

474 proto_major: 1

531 proto_major: 1

475 proto_minor: 1

532 proto_minor: 1

476− content_length: 32560

533+ content_length: 32008

477 host: ""

534 host: ""

478− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Y2LAQF2yCXyV5XuHGMiRiXUs\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_wV7rNKeXv57wTn41fY8P4E2R\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_wV7rNKeXv57wTn41fY8P4E2R\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_EYqplDdiLJqBKLszhf1zFXff\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\",\\\"replace_all\\\":false}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_EYqplDdiLJqBKLszhf1zFXff\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_W5U3KN6Bu45HQ3xHaxcvzlDu\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"hello from crush\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_W5U3KN6Bu45HQ3xHaxcvzlDu\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

535+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_Wa8nxiYWCcBFQAvMGsGLmHCl\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"call_ArFVi3JY4UWeYQo1nG9l2UHy\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_lH6mbJbFqv4bAiHRAuifJsTp\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_lH6mbJbFqv4bAiHRAuifJsTp\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_o0u65HA4wQDn0xJQCE31VJc2\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_o0u65HA4wQDn0xJQCE31VJc2\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_gRff8NsecYHFsCOKKmUYNcuS\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"description\\\":\\\"Run the Go program to test output\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"hello from crush\\n\\n\\n<cwd>/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file</cwd>\",\"tool_call_id\":\"call_gRff8NsecYHFsCOKKmUYNcuS\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

479 headers:

536 headers:

480 Accept:

537 Accept:

481 - application/json

538 - application/json

482 Content-Type:

539 Content-Type:

483 - application/json

540 - application/json

484 User-Agent:

541 User-Agent:

485− - OpenAI/Go 2.3.0

542+ - OpenAI/Go 2.7.1

486 url: https://api.openai.com/v1/chat/completions

543 url: https://api.openai.com/v1/chat/completions

487 method: POST

544 method: POST

488 response:

545 response:

@@ -491,13 +548,13 @@ interactions:

491 proto_minor: 0

548 proto_minor: 0

492 content_length: -1

549 content_length: -1

493 body: |+

550 body: |+

494− data: {"id":"chatcmpl-CQ4I25SOHOeNgzQVPYIdINvTGEZWv","object":"chat.completion.chunk","created":1760329054,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"zgja6xjLQa"}

551+ data: {"id":"chatcmpl-CTntBWAuqcPe8WDYfLWLGBEHDO2Kd","object":"chat.completion.chunk","created":1761219321,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"CQpyPqNUux"}

495

552

496− data: {"id":"chatcmpl-CQ4I25SOHOeNgzQVPYIdINvTGEZWv","object":"chat.completion.chunk","created":1760329054,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"updated"},"finish_reason":null}],"usage":null,"obfuscation":"FZ85x"}

553+ data: {"id":"chatcmpl-CTntBWAuqcPe8WDYfLWLGBEHDO2Kd","object":"chat.completion.chunk","created":1761219321,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"XKcYvMFH"}

497

554

498− data: {"id":"chatcmpl-CQ4I25SOHOeNgzQVPYIdINvTGEZWv","object":"chat.completion.chunk","created":1760329054,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"wVDqRu"}

555+ data: {"id":"chatcmpl-CTntBWAuqcPe8WDYfLWLGBEHDO2Kd","object":"chat.completion.chunk","created":1761219321,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"uFic85"}

499

556

500− data: {"id":"chatcmpl-CQ4I25SOHOeNgzQVPYIdINvTGEZWv","object":"chat.completion.chunk","created":1760329054,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6954,"completion_tokens":4,"total_tokens":6958,"prompt_tokens_details":{"cached_tokens":6784,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"kpaLB"}

557+ data: {"id":"chatcmpl-CTntBWAuqcPe8WDYfLWLGBEHDO2Kd","object":"chat.completion.chunk","created":1761219321,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6895,"completion_tokens":4,"total_tokens":6899,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Kq12tWHV"}

501

558

502 data: [DONE]

559 data: [DONE]

503

560

@@ -506,4 +563,4 @@ interactions:

506 - text/event-stream; charset=utf-8

563 - text/event-stream; charset=utf-8

507 status: 200 OK

564 status: 200 OK

508 code: 200

565 code: 200

509− duration: 1.422256792s

566+ duration: 2.045222709s

internal/agent/testdata/TestCoderAgent/openai-gpt-5/write_tool.yaml+69−75

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.openai.com/v1/chat/completions

20 method: POST

21 response:

@@ -24,23 +24,23 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4xZXmUB6djAMqD"}

27+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"M0bqTtIbWsOVtp"}

29− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9QSNGFDrL7"}

29+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rnV6xaP926"}

31− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" config"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"NdlP6eQQX"}

31+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" config"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4DZr0757E"}

33− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":".json"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1rWY29BUHR5"}

33+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":".json"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"PEuJJcJFYoE"}

35− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MbaOOx8zvV2"}

35+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"flXSEhQvX94"}

37− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" JSON"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WGnVnir3iun"}

37+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" JSON"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LSGxg4WokwO"}

39− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"07K3sZf8"}

39+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"vJiNekBy"}

41− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"3fs9T1uMOb"}

41+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"X4xBihvmE6"}

43− data: {"id":"chatcmpl-CQ4KCByqlwrziZqA97J5dsPSdvwfk","object":"chat.completion.chunk","created":1760329188,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":153,"completion_tokens":6,"total_tokens":159,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"MjBcaUIEL96vKD"}

43+ data: {"id":"chatcmpl-CTnvwI9MP4tHmEZLi5NBiGPvgWYQk","object":"chat.completion.chunk","created":1761219492,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":153,"completion_tokens":6,"total_tokens":159,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"oxcE3zicLOXntl"}

45 data: [DONE]

@@ -49,22 +49,22 @@ interactions:

49 - text/event-stream; charset=utf-8

50 status: 200 OK

51 code: 200

52− duration: 444.867417ms

52+ duration: 1.317672083s

53- id: 1

54 request:

55 proto: HTTP/1.1

56 proto_major: 1

57 proto_minor: 1

58− content_length: 30764

58+ content_length: 29920

59 host: ""

60− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

60+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

61 headers:

62 Accept:

63 - application/json

64 Content-Type:

65 - application/json

66 User-Agent:

67− - OpenAI/Go 2.3.0

67+ - OpenAI/Go 2.7.1

68 url: https://api.openai.com/v1/chat/completions

69 method: POST

70 response:

@@ -73,97 +73,97 @@ interactions:

73 proto_minor: 0

74 content_length: -1

75 body: |+

76− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_4ntxEwLOxJm620ine8gGnN9g","type":"function","function":{"name":"write","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"ODzmNl6XpP9"}

76+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_TjZLEp9jkCTvKKhOz76gkRQh","type":"function","function":{"name":"write","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"81UYdaXIHZB"}

78− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"qfJkKIwnYYJ4Ucm"}

78+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PbN2pEi4UMuBDYa"}

80− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9RwFgnhPl8TMF0"}

80+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iBQX3kmVtChiPv"}

82− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kCjfMj4VkSt6x"}

82+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RpXZc3iq22JC4"}

84− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2P9IAcVG5qDO1uA"}

84+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Cg8U99O4iuJKO9A"}

86− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SUhV6na9TNtB3R6"}

86+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PcGb21Zan6Q7RBM"}

88− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yJ6hfRRdaoKvkCs"}

88+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"90vqa37YnqGFkS4"}

90− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XgEKuvUcZKafwYq"}

90+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FZfjoIJTwlcjydW"}

92− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LiBkgL9rqQ4tRaZ"}

92+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z3b7REaD4XhOVJR"}

94− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QWdSuUJ1i8EQQ"}

94+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wRWZGZAukppU8"}

96− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rnEl2niy6QTSL"}

96+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MiOZXJYM96t0G"}

98− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1bzHIsNlBrLnO"}

98+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zp5j5Tvgwst4x"}

100− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VKHM605Ld3WGu"}

100+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NRv9vKoTRIFjP"}

101

102− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b5PBrn5UTuXe4"}

102+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Fa5sc6lpO6Hpp"}

103

104− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

104+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

105

106− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

106+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

107

108− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

108+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}

109

110− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"}

110+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X"}

111

112− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j"}

112+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A"}

113

114− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/write"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TUUE07UACJUF"}

114+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/write"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oqT0o2skg2rn"}

115

116− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6ojWNFceCVbfa"}

116+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OHrzJxE4sXmn3"}

117

118− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/config"}}]},"finish_reason":null}],"usage":null,"obfuscation":"14lEcKvCbXo"}

118+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/config"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z681EomrhYE"}

119

120− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".json"}}]},"finish_reason":null}],"usage":null,"obfuscation":"F4vmNniMufZoX"}

120+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".json"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kPLvcTyEQp5nU"}

121

122− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PcWRbOtso4R9M"}

122+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"eSlCBkFSP0hIq"}

123

124− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QAy2s4W3P1K"}

124+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VmN3SHI08Qk"}

125

126− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ELXFcaFq21KrS"}

126+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lBKFFTDffaTkD"}

127

128− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"eSG0Cu7VofdQo"}

128+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"GLrzJT464Xlrm"}

129

130− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"name"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jkPvYEHhJrqV0J"}

130+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"name"}}]},"finish_reason":null}],"usage":null,"obfuscation":"J7n7rlZsgtaeZl"}

131

132− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FVGLwUTcrFwtF"}

132+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sHkTCmAFrnhSZ"}

133

134− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mxSTXJNHbVxOK"}

134+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"dAfFHgsSOfMXj"}

135

136− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kCjGDO5JBU6b1N"}

136+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xeXGXTU32v5uCe"}

137

138− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"FxONN8zmL7764"}

138+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"YK3kczWPMPWND"}

139

140− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hCoyd3CXh0IVi"}

140+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"EQK9Eup5a3h1E"}

141

142− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"version"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tY6HcxJabIG"}

142+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"version"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bZizx0ak83k"}

143

144− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Vz5Y31asP4xkN"}

144+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CvquthxPuuB5m"}

145

146− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"IpY7ZRrZbGIjL"}

146+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"UXmuFWhVhX2ZQ"}

147

148− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1"}}]},"finish_reason":null}],"usage":null,"obfuscation":"h"}

148+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z"}

149

150− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}

150+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"a"}

151

152− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"}

152+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"t"}

153

154− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"v"}

154+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"}

155

156− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"}

156+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2"}

157

158− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"NCbr8Q025RkARd"}

158+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Rl4zzYy8elbx8C"}

159

160− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7"}

160+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"J"}

161

162− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KvcekzPgt8itpwt"}

162+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7krRc08w9QylktF"}

163

164− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

164+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}

165

166− data: {"id":"chatcmpl-CQ4KCAhmCSEI1g6gOf1AOIUS94DHG","object":"chat.completion.chunk","created":1760329188,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6589,"completion_tokens":316,"total_tokens":6905,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"H"}

166+ data: {"id":"chatcmpl-CTnvwba8u9amDPNpZXzWIzoGjjP78","object":"chat.completion.chunk","created":1761219492,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6490,"completion_tokens":636,"total_tokens":7126,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"XwGG"}

167

168 data: [DONE]

169

@@ -172,22 +172,22 @@ interactions:

172 - text/event-stream; charset=utf-8

173 status: 200 OK

174 code: 200

175− duration: 7.476178s

175+ duration: 17.913437334s

176- id: 2

177 request:

178 proto: HTTP/1.1

179 proto_major: 1

180 proto_minor: 1

181− content_length: 31253

181+ content_length: 30409

182 host: ""

183− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4ntxEwLOxJm620ine8gGnN9g\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\\",\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\n</result>\",\"tool_call_id\":\"call_4ntxEwLOxJm620ine8gGnN9g\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

183+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_TjZLEp9jkCTvKKhOz76gkRQh\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\\",\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\n</result>\",\"tool_call_id\":\"call_TjZLEp9jkCTvKKhOz76gkRQh\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

184 headers:

185 Accept:

186 - application/json

187 Content-Type:

188 - application/json

189 User-Agent:

190− - OpenAI/Go 2.3.0

190+ - OpenAI/Go 2.7.1

191 url: https://api.openai.com/v1/chat/completions

192 method: POST

193 response:

@@ -196,19 +196,13 @@ interactions:

196 proto_minor: 0

197 content_length: -1

198 body: |+

199− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"tqY6UGzLXa"}

199+ data: {"id":"chatcmpl-CTnwFMOVQzCcST2CZU5upKJrS6cV9","object":"chat.completion.chunk","created":1761219511,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"qykIA2JU8r"}

200

201− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Created"},"finish_reason":null}],"usage":null,"obfuscation":"d7Ywo"}

201+ data: {"id":"chatcmpl-CTnwFMOVQzCcST2CZU5upKJrS6cV9","object":"chat.completion.chunk","created":1761219511,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"tgaflgcz"}

202

203− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"Phk4z6CtcDg"}

203+ data: {"id":"chatcmpl-CTnwFMOVQzCcST2CZU5upKJrS6cV9","object":"chat.completion.chunk","created":1761219511,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"RD2Jcq"}

204

205− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" config"},"finish_reason":null}],"usage":null,"obfuscation":"mIIkz"}

205+ data: {"id":"chatcmpl-CTnwFMOVQzCcST2CZU5upKJrS6cV9","object":"chat.completion.chunk","created":1761219511,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6583,"completion_tokens":4,"total_tokens":6587,"prompt_tokens_details":{"cached_tokens":6400,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"RDPaM"}

206−

207− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".json"},"finish_reason":null}],"usage":null,"obfuscation":"rTAF3El"}

208−

209− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"c9ui79"}

210−

211− data: {"id":"chatcmpl-CQ4KLPQpYDr3yTWbnbTLxKrvvInv7","object":"chat.completion.chunk","created":1760329197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":6682,"completion_tokens":7,"total_tokens":6689,"prompt_tokens_details":{"cached_tokens":6528,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Mei5x"}

212

206

213 data: [DONE]

207 data: [DONE]

214

208

@@ -217,4 +211,4 @@ interactions:

217 - text/event-stream; charset=utf-8

211 - text/event-stream; charset=utf-8

218 status: 200 OK

212 status: 200 OK

219 code: 200

213 code: 200

220− duration: 1.290869167s

214+ duration: 1.55601675s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/bash_tool.yaml+71−142

@@ -6,65 +6,16 @@ interactions:

6 proto: HTTP/1.1

7 proto_major: 1

8 proto_minor: 1

9− content_length: 775

9+ content_length: 29988

10− host: ""

11− body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n<rules>\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse bash to create a file named test.txt with content ''hello bash''\n <think>\n\n</think>","role":"user"}],"model":"qwen/qwen3-next-80b-a3b-instruct","max_tokens":40,"stream_options":{"include_usage":true},"usage":{"include":true},"stream":true}'

12− headers:

13− Accept:

14− - application/json

15− Content-Type:

16− - application/json

17− User-Agent:

18− - OpenAI/Go 2.3.0

19− url: https://openrouter.ai/api/v1/chat/completions

20− method: POST

21− response:

22− proto: HTTP/2.0

23− proto_major: 2

24− proto_minor: 0

25− content_length: -1

26− body: |+

27− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

28−

29− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

30−

31− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

32−

33− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

34−

35− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

36−

37− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello bash using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

38−

39− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

40−

41− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

42−

43− data: {"id":"gen-1760329238-Bh1pHVDXl5tEH7EHb8pa","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.00002964,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001974,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

44−

45− data: [DONE]

46−

47− headers:

48− Content-Type:

49− - text/event-stream

50− status: 200 OK

51− code: 200

52− duration: 776.034042ms

53−- id: 1

54− request:

55− proto: HTTP/1.1

56− proto_major: 1

57− proto_minor: 1

58− content_length: 30758

59 host: ""

10 host: ""

60− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

11+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

61 headers:

12 headers:

62 Accept:

13 Accept:

63 - application/json

14 - application/json

64 Content-Type:

15 Content-Type:

65 - application/json

16 - application/json

66 User-Agent:

17 User-Agent:

67− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

68 url: https://openrouter.ai/api/v1/chat/completions

19 url: https://openrouter.ai/api/v1/chat/completions

69 method: POST

20 method: POST

70 response:

21 response:

@@ -73,71 +24,71 @@ interactions:

73 proto_minor: 0

24 proto_minor: 0

74 content_length: -1

25 content_length: -1

75 body: |+

26 body: |+

76− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.bash:0","index":0,"type":"function","function":{"name":"bash","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.write:0","index":0,"type":"function","function":{"name":"write","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"command"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\">"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".txt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

41+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

43+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

45+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":":["}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

47+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

49+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

100− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

51+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

102− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

53+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

103

104− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"bash"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

55+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

105

106− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\",\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

57+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

107

108− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"arguments"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

59+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

109

110− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

61+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

111

112− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"command"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

63+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

113

114− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

65+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/bash"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

115

116− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\">"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

67+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

117

118− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

69+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

119

120− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".txt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

71+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".txt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

121

122− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\",\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

73+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

123

124− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"description"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

75+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

125

126− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

77+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"content"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

127

128− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Create"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

79+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

129

130− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" empty"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

81+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

131

132− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

83+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

133

134− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

85+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" bash"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

135

136− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"]}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

87+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

137

138− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

89+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

139

140− data: {"id":"gen-1760329238-V63OjudSG8aMyz0ulGAb","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329238,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6895,"completion_tokens":41,"total_tokens":6936,"cost":0.00276695,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00268905,"upstream_inference_completions_cost":0.0000779},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

91+ data: {"id":"gen-1761220121-Nwd8L5a2klih4AqrkBw2","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6796,"completion_tokens":40,"total_tokens":6836,"cost":0.0038574,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0037378,"upstream_inference_completions_cost":0.0001196},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

141

142 data: [DONE]

93 data: [DONE]

143

@@ -146,22 +97,22 @@ interactions:

146 - text/event-stream

97 - text/event-stream

147 status: 200 OK

98 status: 200 OK

148 code: 200

99 code: 200

149− duration: 1.244239833s

100+ duration: 1.384183792s

150−- id: 2

101+- id: 1

151 request:

102 request:

152 proto: HTTP/1.1

103 proto: HTTP/1.1

153 proto_major: 1

104 proto_major: 1

154 proto_minor: 1

105 proto_minor: 1

155− content_length: 31090

106+ content_length: 775

156 host: ""

107 host: ""

157− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.bash:0\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"> test.txt\\\",\\\": \\\":[{\\\"tool\\\":\\\"bash\\\",\\\"arguments\\\":{\\\"command\\\":\\\"> test.txt\\\",\\\"description\\\":\\\"Create empty file\\\"}}]}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"functions.bash:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

108+ body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n<rules>\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse bash to create a file named test.txt with content ''hello bash''\n <think>\n\n</think>","role":"user"}],"model":"qwen/qwen3-next-80b-a3b-instruct","max_tokens":40,"stream_options":{"include_usage":true},"usage":{"include":true},"stream":true}'

158 headers:

109 headers:

159 Accept:

110 Accept:

160 - application/json

111 - application/json

161 Content-Type:

112 Content-Type:

162 - application/json

113 - application/json

163 User-Agent:

114 User-Agent:

164− - OpenAI/Go 2.3.0

115+ - OpenAI/Go 2.7.1

165 url: https://openrouter.ai/api/v1/chat/completions

116 url: https://openrouter.ai/api/v1/chat/completions

166 method: POST

117 method: POST

167 response:

118 response:

@@ -170,51 +121,27 @@ interactions:

170 proto_minor: 0

121 proto_minor: 0

171 content_length: -1

122 content_length: -1

172 body: |+

123 body: |+

173− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

124+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

174

125

175− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"bash:1","type":"function","function":{"name":"bash","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

126+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

176

127

177− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

128+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

178

129

179− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"command"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

130+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

180

131

181− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

132+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

182

133

183− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"echo"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

134+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

184

135

185− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" '"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

136+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

186

137

187− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

138+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":" using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

188

139

189− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" bash"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

140+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

190

141

191− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"'"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

142+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

192

143

193− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" >"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

144+ data: {"id":"gen-1761220121-3hnRPNviwcXEssMoinjY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220121,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.0000213,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000141,"upstream_inference_completions_cost":0.0000072},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

194−

195− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

196−

197− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

198−

199− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\",\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

200−

201− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"description"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

202−

203− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

204−

205− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Write"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

206−

207− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" content"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

208−

209− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" to"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

210−

211− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

212−

213− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

214−

215− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ec889fbb"}

216−

217− data: {"id":"gen-1760329240-seDOpwMgUh2mQNyfSD7U","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329240,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7610,"completion_tokens":29,"total_tokens":7639,"cost":0.009277,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.009132,"upstream_inference_completions_cost":0.000145},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

218

145

219 data: [DONE]

146 data: [DONE]

220

147

@@ -223,22 +150,22 @@ interactions:

223 - text/event-stream

150 - text/event-stream

224 status: 200 OK

151 status: 200 OK

225 code: 200

152 code: 200

226− duration: 2.120776458s

153+ duration: 2.347839917s

227−- id: 3

154+- id: 2

228 request:

155 request:

229 proto: HTTP/1.1

156 proto: HTTP/1.1

230 proto_major: 1

157 proto_major: 1

231 proto_minor: 1

158 proto_minor: 1

232− content_length: 31352

159+ content_length: 30410

233 host: ""

160 host: ""

234− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.bash:0\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"> test.txt\\\",\\\": \\\":[{\\\"tool\\\":\\\"bash\\\",\\\"arguments\\\":{\\\"command\\\":\\\"> test.txt\\\",\\\"description\\\":\\\"Create empty file\\\"}}]}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"functions.bash:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"bash:1\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"echo 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Write content to file\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"bash:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

161+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.write:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool/test.txt\\\", \\\"content\\\": \\\"hello bash\\\"}\",\"name\":\"write\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool/test.txt\\n</result>\",\"tool_call_id\":\"functions.write:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

235 headers:

162 headers:

236 Accept:

163 Accept:

237 - application/json

164 - application/json

238 Content-Type:

165 Content-Type:

239 - application/json

166 - application/json

240 User-Agent:

167 User-Agent:

241− - OpenAI/Go 2.3.0

168+ - OpenAI/Go 2.7.1

242 url: https://openrouter.ai/api/v1/chat/completions

169 url: https://openrouter.ai/api/v1/chat/completions

243 method: POST

170 method: POST

244 response:

171 response:

@@ -247,27 +174,29 @@ interactions:

247 proto_minor: 0

174 proto_minor: 0

248 content_length: -1

175 content_length: -1

249 body: |+

176 body: |+

250− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

177+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

178+

179+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":"Created"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

251

180

252− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":"File"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

181+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

253

182

254− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":" created"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

183+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

255

184

256− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

185+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

257

186

258− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":" content"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

187+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":" content"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

259

188

260− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

189+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

261

190

262− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":"hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

191+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":"hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

263

192

264− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

193+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

265

194

266− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":"'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

195+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":"'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

267

196

268− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

197+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

269

198

270− data: {"id":"gen-1760329242-cQX3Flc8BgawGoXY9Cd6","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329242,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7658,"completion_tokens":9,"total_tokens":7667,"cost":0.0046173,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045948,"upstream_inference_completions_cost":0.0000225},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

199+ data: {"id":"gen-1761220124-48CxqY1cPZZ1JttbJo0X","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220124,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6880,"completion_tokens":10,"total_tokens":6890,"cost":0.0027022,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0026832,"upstream_inference_completions_cost":0.000019},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

271

200

272 data: [DONE]

201 data: [DONE]

273

202

@@ -276,4 +205,4 @@ interactions:

276 - text/event-stream

205 - text/event-stream

277 status: 200 OK

206 status: 200 OK

278 code: 200

207 code: 200

279− duration: 2.11159725s

208+ duration: 2.581500417s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/download_tool.yaml+25−95

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,19 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

29− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":"Download"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":"Download"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

31− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":" robots"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":" robots.txt from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

33− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt from httpbin"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":" http"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

35− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":".org"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":"bin.org"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

37− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

37+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""}

39− data: {"id":"gen-1760329245-1zuYtVSpTCWXPD07DxKF","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329245,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":145,"completion_tokens":8,"total_tokens":153,"cost":0.00003135,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002175,"upstream_inference_completions_cost":0.0000096},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

39+ data: {"id":"gen-1761220127-tE9zrDWy36dYAMdiFQDZ","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":149,"completion_tokens":7,"total_tokens":156,"cost":0.00003285,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002235,"upstream_inference_completions_cost":0.0000105},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

41 data: [DONE]

@@ -45,22 +45,22 @@ interactions:

45 - text/event-stream

46 status: 200 OK

47 code: 200

48− duration: 816.702209ms

48+ duration: 741.712292ms

49- id: 1

50 request:

51 proto: HTTP/1.1

52 proto_major: 1

53 proto_minor: 1

54− content_length: 30775

54+ content_length: 30005

55 host: ""

56− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

57 headers:

58 Accept:

59 - application/json

60 Content-Type:

61 - application/json

62 User-Agent:

63− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

64 url: https://openrouter.ai/api/v1/chat/completions

65 method: POST

66 response:

@@ -69,59 +69,11 @@ interactions:

69 proto_minor: 0

70 content_length: -1

71 body: |+

72− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

72+ data: {"id":"gen-1761220127-P8hlVNqs8LbteZNNJujh","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"download:0","type":"function","function":{"name":"download","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

74+ data: {"id":"gen-1761220127-P8hlVNqs8LbteZNNJujh","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.download:0","function":{"arguments":"{\"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/robots.txt\", \"url\": \"https://httpbin.org/robots.txt\"}","name":"download"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

76− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

76+ data: {"id":"gen-1761220127-P8hlVNqs8LbteZNNJujh","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220127,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7468,"completion_tokens":36,"total_tokens":7504,"cost":0.003806,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.003734,"upstream_inference_completions_cost":0.000072},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

77−

78− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"url"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

79−

80− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

81−

82− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

83−

84− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"https"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

85−

86− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"://"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

87−

88− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"http"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

89−

90− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"bin"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

91−

92− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".org"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

93−

94− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

95−

96− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rob"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

97−

98− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ots"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

99−

100− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

101−

102− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

103−

104− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

105−

106− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

107−

108− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

109−

110− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

111−

112− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

113−

114− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rob"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

115−

116− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ots"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

117−

118− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

119−

120− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

121−

122− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

123−

124− data: {"id":"gen-1760329245-wHiUbBpxnVdKscWkp0LW","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329257,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7556,"completion_tokens":32,"total_tokens":7588,"cost":0.0046136,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045336,"upstream_inference_completions_cost":0.00008},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

125

126 data: [DONE]

78 data: [DONE]

127

@@ -130,7 +82,7 @@ interactions:

130 - text/event-stream

82 - text/event-stream

131 status: 200 OK

83 status: 200 OK

132 code: 200

84 code: 200

133− duration: 10.174061625s

85+ duration: 590.544084ms

134- id: 2

86- id: 2

135 request:

87 request:

136 proto: HTTP/1.1

88 proto: HTTP/1.1

@@ -156,22 +108,22 @@ interactions:

156 - text/plain

108 - text/plain

157 status: 200 OK

109 status: 200 OK

158 code: 200

110 code: 200

159− duration: 630.41ms

111+ duration: 3.159789083s

160- id: 3

112- id: 3

161 request:

113 request:

162 proto: HTTP/1.1

114 proto: HTTP/1.1

163 proto_major: 1

115 proto_major: 1

164 proto_minor: 1

116 proto_minor: 1

165− content_length: 31165

117+ content_length: 30479

166 host: ""

118 host: ""

167− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"download:0\",\"function\":{\"arguments\":\"{\\\"url\\\": \\\"https://httpbin.org/robots.txt\\\", \\\"file_path\\\": \\\"robots.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/robots.txt (Content-Type: text/plain)\",\"tool_call_id\":\"download:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

119+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.download:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/robots.txt\\\", \\\"url\\\": \\\"https://httpbin.org/robots.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/robots.txt (Content-Type: text/plain)\",\"tool_call_id\":\"functions.download:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

168 headers:

120 headers:

169 Accept:

121 Accept:

170 - application/json

122 - application/json

171 Content-Type:

123 Content-Type:

172 - application/json

124 - application/json

173 User-Agent:

125 User-Agent:

174− - OpenAI/Go 2.3.0

126+ - OpenAI/Go 2.7.1

175 url: https://openrouter.ai/api/v1/chat/completions

127 url: https://openrouter.ai/api/v1/chat/completions

176 method: POST

128 method: POST

177 response:

129 response:

@@ -180,35 +132,13 @@ interactions:

180 proto_minor: 0

132 proto_minor: 0

181 content_length: -1

133 content_length: -1

182 body: |+

134 body: |+

183− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

135+ data: {"id":"gen-1761220132-JkmUEyIgU4JHAUiK8aZL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220132,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

184−

185− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

186−

187− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

188−

189− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" The"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

190−

191− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" robots"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

192−

193− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

194−

195− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

196−

197− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" has"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

198−

199− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" been"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

200−

201− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" downloaded"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

202−

203− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

204−

205− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":" saved"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

206

136

207− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

137+ data: {"id":"gen-1761220132-JkmUEyIgU4JHAUiK8aZL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220132,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

208

138

209− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

139+ data: {"id":"gen-1761220132-JkmUEyIgU4JHAUiK8aZL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220132,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

210

140

211− data: {"id":"gen-1760329261-PCxnxDRCWNpcKbnqNEcD","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329261,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6978,"completion_tokens":13,"total_tokens":6991,"cost":0.0042193,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0041868,"upstream_inference_completions_cost":0.0000325},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

141+ data: {"id":"gen-1761220132-JkmUEyIgU4JHAUiK8aZL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220132,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7554,"completion_tokens":2,"total_tokens":7556,"cost":0.0045374,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045324,"upstream_inference_completions_cost":0.000005},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

212

142

213 data: [DONE]

143 data: [DONE]

214

144

@@ -217,4 +147,4 @@ interactions:

217 - text/event-stream

147 - text/event-stream

218 status: 200 OK

148 status: 200 OK

219 code: 200

149 code: 200

220− duration: 986.589334ms

150+ duration: 4.4081085s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/fetch_tool.yaml+116−43

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,23 +24,35 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":"Check"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":"Check"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":" if"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":" if https"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":" https"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":"://httpbin.org"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":"://"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":"/html contains the word"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":"http"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":" Herman"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":"bin"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

41− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

41+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":".org"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

43− data: {"id":"gen-1760329262-gXcDcJIJdCaivVwtSLyj","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329262,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":148,"completion_tokens":13,"total_tokens":161,"cost":0.00003502,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002072,"upstream_inference_completions_cost":0.0000143},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

43+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":"/html"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

44+

45+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":" contains"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

46+

47+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

48+

49+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":" word"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

50+

51+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":" Herman"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

52+

53+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

54+

55+ data: {"id":"gen-1761220136-Mu7F3XkI1jeGXwNzFmFC","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":148,"completion_tokens":13,"total_tokens":161,"cost":0.0000417,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000222,"upstream_inference_completions_cost":0.0000195},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

45 data: [DONE]

57 data: [DONE]

@@ -49,22 +61,22 @@ interactions:

49 - text/event-stream

61 - text/event-stream

50 status: 200 OK

62 status: 200 OK

51 code: 200

63 code: 200

52− duration: 812.382041ms

64+ duration: 658.333959ms

53- id: 1

65- id: 1

54 request:

66 request:

55 proto: HTTP/1.1

67 proto: HTTP/1.1

56 proto_major: 1

68 proto_major: 1

57 proto_minor: 1

69 proto_minor: 1

58− content_length: 30785

70+ content_length: 30015

59 host: ""

71 host: ""

60− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

72+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

61 headers:

73 headers:

62 Accept:

74 Accept:

63 - application/json

75 - application/json

64 Content-Type:

76 Content-Type:

65 - application/json

77 - application/json

66 User-Agent:

78 User-Agent:

67− - OpenAI/Go 2.3.0

79+ - OpenAI/Go 2.7.1

68 url: https://openrouter.ai/api/v1/chat/completions

80 url: https://openrouter.ai/api/v1/chat/completions

69 method: POST

81 method: POST

70 response:

82 response:

@@ -73,41 +85,82 @@ interactions:

73 proto_minor: 0

85 proto_minor: 0

74 content_length: -1

86 content_length: -1

75 body: |+

87 body: |+

76− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88+ data: {"id":"gen-1761220136-XcNHjmV9JVq643s0XNe9","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.fetch:0","index":0,"type":"function","function":{"name":"fetch","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90+ data: {"id":"gen-1761220136-XcNHjmV9JVq643s0XNe9","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.fetch:0","function":{"arguments":"{\"format\": \".text\", \"url\": \"https://httpbin.org/html\"}","name":"fetch"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

80− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"url"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92+ data: {"id":"gen-1761220136-XcNHjmV9JVq643s0XNe9","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220136,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7471,"completion_tokens":16,"total_tokens":7487,"cost":0.0037675,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0037355,"upstream_inference_completions_cost":0.000032},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

82− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94+ data: [DONE]

84− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96+ headers:

97+ Content-Type:

98+ - text/event-stream

99+ status: 200 OK

100+ code: 200

101+ duration: 665.546417ms

102+- id: 2

103+ request:

104+ proto: HTTP/1.1

105+ proto_major: 1

106+ proto_minor: 1

107+ content_length: 30308

108+ host: ""

109+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.fetch:0\",\"function\":{\"arguments\":\"{\\\"format\\\": \\\".text\\\", \\\"url\\\": \\\"https://httpbin.org/html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Format must be one of: text, markdown, html\",\"tool_call_id\":\"functions.fetch:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

110+ headers:

111+ Accept:

112+ - application/json

113+ Content-Type:

114+ - application/json

115+ User-Agent:

116+ - OpenAI/Go 2.7.1

117+ url: https://openrouter.ai/api/v1/chat/completions

118+ method: POST

119+ response:

120+ proto: HTTP/2.0

121+ proto_major: 2

122+ proto_minor: 0

123+ content_length: -1

124+ body: |+

125+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

126+

127+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.fetch:1","index":0,"type":"function","function":{"name":"fetch","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

128

86− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"https"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

129+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"format"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

130

88− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"://"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

131+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

132

90− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"http"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

133+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

134

92− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"bin"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

135+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"text"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

136

94− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".org"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

137+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

138

96− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/html"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

139+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

140

98− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\",\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

141+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"url"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

142

100− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"format"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

143+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

144

102− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

145+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

103

146

104− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"text"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

147+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"https"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

105

148

106− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

149+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"://"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

107

150

108− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

151+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"http"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

109

152

110− data: {"id":"gen-1760329262-CSJLi1aToyF0fPW82biB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329275,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6903,"completion_tokens":25,"total_tokens":6928,"cost":0.00273967,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00269217,"upstream_inference_completions_cost":0.0000475},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

153+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"bin"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

154+

155+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".org"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

156+

157+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/html"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

158+

159+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

160+

161+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

162+

163+ data: {"id":"gen-1761220138-JFmDWWudGgefgweJl7na","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220139,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6857,"completion_tokens":27,"total_tokens":6884,"cost":0.0041817,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0041142,"upstream_inference_completions_cost":0.0000675},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

111

164

112 data: [DONE]

165 data: [DONE]

113

166

@@ -116,8 +169,8 @@ interactions:

116 - text/event-stream

169 - text/event-stream

117 status: 200 OK

170 status: 200 OK

118 code: 200

171 code: 200

119− duration: 10.173146166s

172+ duration: 1.634766083s

120−- id: 2

173+- id: 3

121 request:

174 request:

122 proto: HTTP/1.1

175 proto: HTTP/1.1

123 proto_major: 1

176 proto_major: 1

@@ -154,22 +207,22 @@ interactions:

154 - text/html; charset=utf-8

207 - text/html; charset=utf-8

155 status: 200 OK

208 status: 200 OK

156 code: 200

209 code: 200

157− duration: 125.777917ms

210+ duration: 1.956989167s

158−- id: 3

211+- id: 4

159 request:

212 request:

160 proto: HTTP/1.1

213 proto: HTTP/1.1

161 proto_major: 1

214 proto_major: 1

162 proto_minor: 1

215 proto_minor: 1

163− content_length: 34627

216+ content_length: 34153

164 host: ""

217 host: ""

165− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.fetch:0\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://httpbin.org/html\\\",\\\"format\\\":\\\"text\\\"}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"tool_call_id\":\"functions.fetch:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

218+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.fetch:0\",\"function\":{\"arguments\":\"{\\\"format\\\": \\\".text\\\", \\\"url\\\": \\\"https://httpbin.org/html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Format must be one of: text, markdown, html\",\"tool_call_id\":\"functions.fetch:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"functions.fetch:1\",\"function\":{\"arguments\":\"{\\\"format\\\": \\\"text\\\", \\\"url\\\": \\\"https://httpbin.org/html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"tool_call_id\":\"functions.fetch:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

166 headers:

219 headers:

167 Accept:

220 Accept:

168 - application/json

221 - application/json

169 Content-Type:

222 Content-Type:

170 - application/json

223 - application/json

171 User-Agent:

224 User-Agent:

172− - OpenAI/Go 2.3.0

225+ - OpenAI/Go 2.7.1

173 url: https://openrouter.ai/api/v1/chat/completions

226 url: https://openrouter.ai/api/v1/chat/completions

174 method: POST

227 method: POST

175 response:

228 response:

@@ -178,11 +231,31 @@ interactions:

178 proto_minor: 0

231 proto_minor: 0

179 content_length: -1

232 content_length: -1

180 body: |+

233 body: |+

181− data: {"id":"gen-1760329277-I4SzFb5naFmoLPSw3Rov","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329291,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

234+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

235+

236+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":"Yes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

237+

238+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

239+

240+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":" it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

241+

242+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":" contains"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

243+

244+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

245+

246+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":" word"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

247+

248+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

249+

250+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":"H"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

251+

252+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":"erman"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

253+

254+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":"'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

182

255

183− data: {"id":"gen-1760329277-I4SzFb5naFmoLPSw3Rov","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329291,"choices":[{"index":0,"delta":{"role":"assistant","content":"Yes, the content contains the word 'Herman'."},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

256+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"}

184

257

185− data: {"id":"gen-1760329277-I4SzFb5naFmoLPSw3Rov","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329291,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":8172,"completion_tokens":11,"total_tokens":8183,"cost":0.004108,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.004086,"upstream_inference_completions_cost":0.000022},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

258+ data: {"id":"gen-1761220142-p99WbmTME6QMWAONZHWt","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220142,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":8393,"completion_tokens":11,"total_tokens":8404,"cost":0.0050633,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0050358,"upstream_inference_completions_cost":0.0000275},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

186

259

187 data: [DONE]

260 data: [DONE]

188

261

@@ -191,4 +264,4 @@ interactions:

191 - text/event-stream

264 - text/event-stream

192 status: 200 OK

265 status: 200 OK

193 code: 200

266 code: 200

194− duration: 10.205140458s

267+ duration: 4.635297416s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/glob_tool.yaml+29−31

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,19 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

27+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

29+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":" all .go files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

31+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":" all .go files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":" in current directory using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

33+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":" in current directory using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":" glob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

35+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":" glob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""}

37+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

39− data: {"id":"gen-1760329292-UOnTSTc1fEDQ8I59sZmm","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":139,"completion_tokens":11,"total_tokens":150,"cost":0.00003486,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001946,"upstream_inference_completions_cost":0.0000154},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

39+ data: {"id":"gen-1761220147-yrFSxn0jeR2lqTpz982z","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":139,"completion_tokens":11,"total_tokens":150,"cost":0.00003405,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002085,"upstream_inference_completions_cost":0.0000132},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

41 data: [DONE]

@@ -45,22 +45,22 @@ interactions:

45 - text/event-stream

46 status: 200 OK

47 code: 200

48− duration: 964.9115ms

48+ duration: 443.75725ms

49- id: 1

50 request:

51 proto: HTTP/1.1

52 proto_major: 1

53 proto_minor: 1

54− content_length: 30747

54+ content_length: 29977

55 host: ""

56− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

57 headers:

58 Accept:

59 - application/json

60 Content-Type:

61 - application/json

62 User-Agent:

63− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

64 url: https://openrouter.ai/api/v1/chat/completions

65 method: POST

66 response:

@@ -69,25 +69,23 @@ interactions:

69 proto_minor: 0

70 content_length: -1

71 body: |+

72− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

72+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.glob:0","index":0,"type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.glob:0","index":0,"type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"pattern"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"pattern"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"*."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"*."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

88− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

88+ data: {"id":"gen-1761220147-NO5RY2T5TA4WqVVjNLLw","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220147,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6794,"completion_tokens":16,"total_tokens":6810,"cost":0.0041164,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0040764,"upstream_inference_completions_cost":0.00004},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

89−

90− data: {"id":"gen-1760329292-l1MFwnTJvhlkTGZTyy5x","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329292,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6893,"completion_tokens":17,"total_tokens":6910,"cost":0.00272057,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00268827,"upstream_inference_completions_cost":0.0000323},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

92 data: [DONE]

90 data: [DONE]

@@ -96,22 +94,22 @@ interactions:

96 - text/event-stream

94 - text/event-stream

97 status: 200 OK

95 status: 200 OK

98 code: 200

96 code: 200

99− duration: 1.126203375s

97+ duration: 1.073430625s

100- id: 2

98- id: 2

101 request:

99 request:

102 proto: HTTP/1.1

100 proto: HTTP/1.1

103 proto_major: 1

101 proto_major: 1

104 proto_minor: 1

102 proto_minor: 1

105− content_length: 31021

103+ content_length: 30252

106 host: ""

104 host: ""

107− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool/main.go\",\"tool_call_id\":\"functions.glob:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

105+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool/main.go\",\"tool_call_id\":\"functions.glob:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

108 headers:

106 headers:

109 Accept:

107 Accept:

110 - application/json

108 - application/json

111 Content-Type:

109 Content-Type:

112 - application/json

110 - application/json

113 User-Agent:

111 User-Agent:

114− - OpenAI/Go 2.3.0

112+ - OpenAI/Go 2.7.1

115 url: https://openrouter.ai/api/v1/chat/completions

113 url: https://openrouter.ai/api/v1/chat/completions

116 method: POST

114 method: POST

117 response:

115 response:

@@ -120,11 +118,11 @@ interactions:

120 proto_minor: 0

118 proto_minor: 0

121 content_length: -1

119 content_length: -1

122 body: |+

120 body: |+

123− data: {"id":"gen-1760329293-yCtKqDuUOyrempm7VxkN","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329293,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

121+ data: {"id":"gen-1761220148-8aGcfYUfCElMFLprwIW6","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220148,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

124

122

125− data: {"id":"gen-1760329293-yCtKqDuUOyrempm7VxkN","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329293,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found 1 Go file: `/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool/main.go`"},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

123+ data: {"id":"gen-1761220148-8aGcfYUfCElMFLprwIW6","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220148,"choices":[{"index":0,"delta":{"role":"assistant","content":"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool/main.go"},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

126

124

127− data: {"id":"gen-1760329293-yCtKqDuUOyrempm7VxkN","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329293,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7337,"completion_tokens":26,"total_tokens":7363,"cost":0.0037205,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0036685,"upstream_inference_completions_cost":0.000052},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

125+ data: {"id":"gen-1761220148-8aGcfYUfCElMFLprwIW6","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220148,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6902,"completion_tokens":18,"total_tokens":6920,"cost":0.003487,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.003451,"upstream_inference_completions_cost":0.000036},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

128

126

129 data: [DONE]

127 data: [DONE]

130

128

@@ -133,4 +131,4 @@ interactions:

133 - text/event-stream

131 - text/event-stream

134 status: 200 OK

132 status: 200 OK

135 code: 200

133 code: 200

136− duration: 438.354541ms

134+ duration: 644.354708ms

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/grep_tool.yaml+61−49

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,17 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329569-6a0Jj1oG8w5pgboWCl1E","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329569,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329569-6a0Jj1oG8w5pgboWCl1E","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329569,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329569-6a0Jj1oG8w5pgboWCl1E","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329569,"choices":[{"index":0,"delta":{"role":"assistant","content":" for package in Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329569-6a0Jj1oG8w5pgboWCl1E","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329569,"choices":[{"index":0,"delta":{"role":"assistant","content":" files using grep"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":" for package in Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329569-6a0Jj1oG8w5pgboWCl1E","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329569,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

35+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":" files using grep"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329569-6a0Jj1oG8w5pgboWCl1E","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329569,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":140,"completion_tokens":9,"total_tokens":149,"cost":0.0000345,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000021,"upstream_inference_completions_cost":0.0000135},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

37+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

38+

39+ data: {"id":"gen-1761220149-7J9TfUlbjCYqpFghw9UA","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":140,"completion_tokens":9,"total_tokens":149,"cost":0.0000295,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000196,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

39 data: [DONE]

41 data: [DONE]

@@ -43,22 +45,22 @@ interactions:

43 - text/event-stream

45 - text/event-stream

44 status: 200 OK

46 status: 200 OK

45 code: 200

47 code: 200

46− duration: 908.604334ms

48+ duration: 303.891625ms

47- id: 1

49- id: 1

48 request:

50 request:

49 proto: HTTP/1.1

51 proto: HTTP/1.1

50 proto_major: 1

52 proto_major: 1

51 proto_minor: 1

53 proto_minor: 1

52− content_length: 30745

54+ content_length: 29975

53 host: ""

55 host: ""

54− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

55 headers:

57 headers:

56 Accept:

58 Accept:

57 - application/json

59 - application/json

58 Content-Type:

60 Content-Type:

59 - application/json

61 - application/json

60 User-Agent:

62 User-Agent:

61− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

62 url: https://openrouter.ai/api/v1/chat/completions

64 url: https://openrouter.ai/api/v1/chat/completions

63 method: POST

65 method: POST

64 response:

66 response:

@@ -67,51 +69,37 @@ interactions:

67 proto_minor: 0

69 proto_minor: 0

68 content_length: -1

70 content_length: -1

69 body: |+

71 body: |+

70− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

72+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

71−

72− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"grep:0","type":"function","function":{"name":"grep"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

73−

74− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

75−

76− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"pattern"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

77−

78− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

80− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

74+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.grep:0","index":0,"type":"function","function":{"name":"grep","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"package"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

76+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"pattern"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

78+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

80+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"lit"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

82+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"*"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ereal"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

84+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"package"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_text"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

86+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".*"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

88+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\",\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" true"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

90+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"include"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

92+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

100− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

94+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"*."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

102− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"include"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

96+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

103

104− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

98+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

105

106− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"*."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

100+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

107

101

108− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

102+ data: {"id":"gen-1761220149-0vCUfPBSRCS3h7qNhgPs","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220149,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6795,"completion_tokens":24,"total_tokens":6819,"cost":0.00269565,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00265005,"upstream_inference_completions_cost":0.0000456},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

109−

110− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

111−

112− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

113−

114− data: {"id":"gen-1760329569-hPBZT06hbcBXIquctuzu","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329570,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7551,"completion_tokens":29,"total_tokens":7580,"cost":0.0046031,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045306,"upstream_inference_completions_cost":0.0000725},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

115

103

116 data: [DONE]

104 data: [DONE]

117

105

@@ -120,22 +108,22 @@ interactions:

120 - text/event-stream

108 - text/event-stream

121 status: 200 OK

109 status: 200 OK

122 code: 200

110 code: 200

123− duration: 3.257982709s

111+ duration: 920.239083ms

124- id: 2

112- id: 2

125 request:

113 request:

126 proto: HTTP/1.1

114 proto: HTTP/1.1

127 proto_major: 1

115 proto_major: 1

128 proto_minor: 1

116 proto_minor: 1

129− content_length: 31095

117+ content_length: 30329

130 host: ""

118 host: ""

131− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"grep:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"package\\\", \\\"litereal_text\\\": true, \\\"include\\\": \\\"*.go\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool/main.go:\\n Line 1: package main\\n\",\"tool_call_id\":\"grep:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

119+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.grep:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\".*package.*\\\",\\\"include\\\":\\\"*.go\\\"}\",\"name\":\"grep\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"functions.grep:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

132 headers:

120 headers:

133 Accept:

121 Accept:

134 - application/json

122 - application/json

135 Content-Type:

123 Content-Type:

136 - application/json

124 - application/json

137 User-Agent:

125 User-Agent:

138− - OpenAI/Go 2.3.0

126+ - OpenAI/Go 2.7.1

139 url: https://openrouter.ai/api/v1/chat/completions

127 url: https://openrouter.ai/api/v1/chat/completions

140 method: POST

128 method: POST

141 response:

129 response:

@@ -144,11 +132,35 @@ interactions:

144 proto_minor: 0

132 proto_minor: 0

145 content_length: -1

133 content_length: -1

146 body: |+

134 body: |+

147− data: {"id":"gen-1760329573-8rRBrsSYYKEVvtgUxwRI","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329573,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

135+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

136+

137+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

138+

139+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

140+

141+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

142+

143+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":" match"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

144+

145+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

146+

147+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

148+

149+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

150+

151+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

152+

153+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

154+

155+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":"package"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

156+

157+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

158+

159+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

148

160

149− data: {"id":"gen-1760329573-8rRBrsSYYKEVvtgUxwRI","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329573,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found 1 match in main.go:\n```go\nLine 1: package main\n```"},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

161+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

150

162

151− data: {"id":"gen-1760329573-8rRBrsSYYKEVvtgUxwRI","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329573,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7362,"completion_tokens":19,"total_tokens":7381,"cost":0.003719,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.003681,"upstream_inference_completions_cost":0.000038},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

163+ data: {"id":"gen-1761220150-GbZ5zd1G2tyyDqd4dYyy","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220150,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6872,"completion_tokens":13,"total_tokens":6885,"cost":0.00270478,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00268008,"upstream_inference_completions_cost":0.0000247},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

152

164

153 data: [DONE]

165 data: [DONE]

154

166

@@ -157,4 +169,4 @@ interactions:

157 - text/event-stream

169 - text/event-stream

158 status: 200 OK

170 status: 200 OK

159 code: 200

171 code: 200

160− duration: 810.186667ms

172+ duration: 3.372464917s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/ls_tool.yaml+50−52

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,17 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329311-uB6hzbvaeNOL4hazdZZ9","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329311,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

27+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329311-uB6hzbvaeNOL4hazdZZ9","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329311,"choices":[{"index":0,"delta":{"role":"assistant","content":"List"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

29+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":"List"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329311-uB6hzbvaeNOL4hazdZZ9","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329311,"choices":[{"index":0,"delta":{"role":"assistant","content":" files in current directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

31+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":" files in current directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329311-uB6hzbvaeNOL4hazdZZ9","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329311,"choices":[{"index":0,"delta":{"role":"assistant","content":" using ls"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

33+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329311-uB6hzbvaeNOL4hazdZZ9","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329311,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""}

35+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":" ls"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329311-uB6hzbvaeNOL4hazdZZ9","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329311,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":137,"completion_tokens":8,"total_tokens":145,"cost":0.00003038,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001918,"upstream_inference_completions_cost":0.0000112},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

37+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

38+

39+ data: {"id":"gen-1761220154-2UqtOzAtoy23ybbCDhgp","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":137,"completion_tokens":8,"total_tokens":145,"cost":0.00003015,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002055,"upstream_inference_completions_cost":0.0000096},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

39 data: [DONE]

41 data: [DONE]

@@ -43,22 +45,22 @@ interactions:

43 - text/event-stream

45 - text/event-stream

44 status: 200 OK

46 status: 200 OK

45 code: 200

47 code: 200

46− duration: 811.323291ms

48+ duration: 452.08625ms

47- id: 1

49- id: 1

48 request:

50 request:

49 proto: HTTP/1.1

51 proto: HTTP/1.1

50 proto_major: 1

52 proto_major: 1

51 proto_minor: 1

53 proto_minor: 1

52− content_length: 30739

54+ content_length: 29969

53 host: ""

55 host: ""

54− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

55 headers:

57 headers:

56 Accept:

58 Accept:

57 - application/json

59 - application/json

58 Content-Type:

60 Content-Type:

59 - application/json

61 - application/json

60 User-Agent:

62 User-Agent:

61− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

62 url: https://openrouter.ai/api/v1/chat/completions

64 url: https://openrouter.ai/api/v1/chat/completions

63 method: POST

65 method: POST

64 response:

66 response:

@@ -67,53 +69,53 @@ interactions:

67 proto_minor: 0

69 proto_minor: 0

68 content_length: -1

70 content_length: -1

69 body: |+

71 body: |+

70− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

72+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

72− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.ls:0","index":0,"type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.ls:0","index":0,"type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

100+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

100− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

102+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

103

102− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

104+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

103

105

104− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

106+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

105

107

106− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

108+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

107

109

108− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"ls"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

110+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"ls"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

109

111

110− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

112+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

111

113

112− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

114+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

113

115

114− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

116+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

115

117

116− data: {"id":"gen-1760329311-T67Mlv0e55rDpZtkBqdZ","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329324,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6891,"completion_tokens":32,"total_tokens":6923,"cost":0.00274829,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00268749,"upstream_inference_completions_cost":0.0000608},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

118+ data: {"id":"gen-1761220154-2jRV59AxErw9p37yCN59","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220154,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6792,"completion_tokens":32,"total_tokens":6824,"cost":0.00270968,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00264888,"upstream_inference_completions_cost":0.0000608},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

117

119

118 data: [DONE]

120 data: [DONE]

119

121

@@ -122,22 +124,22 @@ interactions:

122 - text/event-stream

124 - text/event-stream

123 status: 200 OK

125 status: 200 OK

124 code: 200

126 code: 200

125− duration: 10.187991041s

127+ duration: 2.121841625s

126- id: 2

128- id: 2

127 request:

129 request:

128 proto: HTTP/1.1

130 proto: HTTP/1.1

129 proto_major: 1

131 proto_major: 1

130 proto_minor: 1

132 proto_minor: 1

131− content_length: 31079

133+ content_length: 30309

132 host: ""

134 host: ""

133− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.ls:0\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"functions.ls:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

135+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.ls:0\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\\"}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"functions.ls:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

134 headers:

136 headers:

135 Accept:

137 Accept:

136 - application/json

138 - application/json

137 Content-Type:

139 Content-Type:

138 - application/json

140 - application/json

139 User-Agent:

141 User-Agent:

140− - OpenAI/Go 2.3.0

142+ - OpenAI/Go 2.7.1

141 url: https://openrouter.ai/api/v1/chat/completions

143 url: https://openrouter.ai/api/v1/chat/completions

142 method: POST

144 method: POST

143 response:

145 response:

@@ -146,25 +148,21 @@ interactions:

146 proto_minor: 0

148 proto_minor: 0

147 content_length: -1

149 content_length: -1

148 body: |+

150 body: |+

149− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

151+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

150−

151− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

152−

153− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":" go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

154

152

155− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":".mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

153+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

156

154

157− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

155+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":".mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

158

156

159− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

157+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

160

158

161− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

159+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":"main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

162

160

163− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

161+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

164

162

165− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

163+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

166

164

167− data: {"id":"gen-1760329326-iqgxqL2btHTf2pURMYXX","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329326,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6968,"completion_tokens":8,"total_tokens":6976,"cost":0.00273272,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00271752,"upstream_inference_completions_cost":0.0000152},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

165+ data: {"id":"gen-1761220157-ngf8iEkZSJ0RaCEBZGhw","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220157,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6869,"completion_tokens":6,"total_tokens":6875,"cost":0.00379589,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00377795,"upstream_inference_completions_cost":0.00001794},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

168

166

169 data: [DONE]

167 data: [DONE]

170

168

@@ -173,4 +171,4 @@ interactions:

173 - text/event-stream

171 - text/event-stream

174 status: 200 OK

172 status: 200 OK

175 code: 200

173 code: 200

176− duration: 1.25833875s

174+ duration: 1.038783667s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/multiedit_tool.yaml+157−323

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,23 +24,37 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":"Use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":"Use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" multiedit to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" update greeting"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" and add comment in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" main.go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

41− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

41+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" greeting"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

43− data: {"id":"gen-1760329327-WR0ufjE3lWtTXlrGOndS","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":160,"completion_tokens":14,"total_tokens":174,"cost":0.0000378,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000224,"upstream_inference_completions_cost":0.0000154},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

43+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

44+

45+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" add"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

46+

47+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

48+

49+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

50+

51+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

52+

53+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

54+

55+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

56+

57+ data: {"id":"gen-1761220158-JV8yYutHEaAKsY4jNUnm","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":160,"completion_tokens":14,"total_tokens":174,"cost":0.000045,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000024,"upstream_inference_completions_cost":0.000021},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

45 data: [DONE]

59 data: [DONE]

@@ -49,22 +63,22 @@ interactions:

49 - text/event-stream

63 - text/event-stream

50 status: 200 OK

64 status: 200 OK

51 code: 200

65 code: 200

52− duration: 883.212125ms

66+ duration: 648.632417ms

53- id: 1

67- id: 1

54 request:

68 request:

55 proto: HTTP/1.1

69 proto: HTTP/1.1

56 proto_major: 1

70 proto_major: 1

57 proto_minor: 1

71 proto_minor: 1

58− content_length: 30825

72+ content_length: 30055

59 host: ""

73 host: ""

60− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

74+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

61 headers:

75 headers:

62 Accept:

76 Accept:

63 - application/json

77 - application/json

64 Content-Type:

78 Content-Type:

65 - application/json

79 - application/json

66 User-Agent:

80 User-Agent:

67− - OpenAI/Go 2.3.0

81+ - OpenAI/Go 2.7.1

68 url: https://openrouter.ai/api/v1/chat/completions

82 url: https://openrouter.ai/api/v1/chat/completions

69 method: POST

83 method: POST

70 response:

84 response:

@@ -73,115 +87,13 @@ interactions:

73 proto_minor: 0

87 proto_minor: 0

74 content_length: -1

88 content_length: -1

75 body: |+

89 body: |+

76− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

90+ data: {"id":"gen-1761220158-FY9L7bXk3wwCeduthrTk","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

77−

78− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":"I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

79−

80− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" help"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

81−

82− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" you"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

83−

84− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" make"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

85−

86− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" those"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

87−

88− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

89−

90− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

91−

92− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

93−

94− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

95−

96− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

97−

98− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

99−

100− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

101−

102− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

103−

104− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

105−

106− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" First"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

107−

108− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

109−

110− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" let"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

111−

112− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" me"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

113−

114− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" check"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

115−

116− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

117−

118− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

119−

120− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" content"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

121−

122− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" of"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

123−

124− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

125−

126− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

127−

128− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

129−

130− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:0","type":"function","function":{"name":"view"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

131−

132− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

133−

134− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

135−

136− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

137−

138− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

139−

140− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

141−

142− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

143−

144− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

145−

146− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

147−

148− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

149−

150− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

151−

152− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

153−

154− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

155−

156− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

157−

158− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

159−

160− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

161−

162− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

163

164− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

92+ data: {"id":"gen-1761220158-FY9L7bXk3wwCeduthrTk","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":"I'll help you make those changes to main.go using multiedit. Let me first read the file to see its current contents."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

165

166− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

94+ data: {"id":"gen-1761220158-FY9L7bXk3wwCeduthrTk","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","function":{"arguments":"{\"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\"}","name":"view"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

167

168− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/mult"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

96+ data: {"id":"gen-1761220158-FY9L7bXk3wwCeduthrTk","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220158,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7481,"completion_tokens":53,"total_tokens":7534,"cost":0.0038465,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0037405,"upstream_inference_completions_cost":0.000106},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

169−

170− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ied"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

171−

172− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"it"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

173−

174− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

175−

176− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

177−

178− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

179−

180− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

181−

182− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

183−

184− data: {"id":"gen-1760329327-2hdxHZrJslxxxcUW4PYI","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329327,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7572,"completion_tokens":60,"total_tokens":7632,"cost":0.0046932,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045432,"upstream_inference_completions_cost":0.00015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

185

186 data: [DONE]

98 data: [DONE]

187

@@ -190,22 +102,22 @@ interactions:

190 - text/event-stream

102 - text/event-stream

191 status: 200 OK

103 status: 200 OK

192 code: 200

104 code: 200

193− duration: 2.009054875s

105+ duration: 647.317792ms

194- id: 2

106- id: 2

195 request:

107 request:

196 proto: HTTP/1.1

108 proto: HTTP/1.1

197 proto_major: 1

109 proto_major: 1

198 proto_minor: 1

110 proto_minor: 1

199− content_length: 31361

111+ content_length: 30614

200 host: ""

112 host: ""

201− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you make those changes to main.go using multiedit. First, let me check the current content of the file.\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

113+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you make those changes to main.go using multiedit. Let me first read the file to see its current contents.\",\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

202 headers:

114 headers:

203 Accept:

115 Accept:

204 - application/json

116 - application/json

205 Content-Type:

117 Content-Type:

206 - application/json

118 - application/json

207 User-Agent:

119 User-Agent:

208− - OpenAI/Go 2.3.0

120+ - OpenAI/Go 2.7.1

209 url: https://openrouter.ai/api/v1/chat/completions

121 url: https://openrouter.ai/api/v1/chat/completions

210 method: POST

122 method: POST

211 response:

123 response:

@@ -214,205 +126,207 @@ interactions:

214 proto_minor: 0

126 proto_minor: 0

215 content_length: -1

127 content_length: -1

216 body: |+

128 body: |+

217− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"Now"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

129+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

130+

131+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"Now"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

218

132

219− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

133+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

220

134

221− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

135+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

222

136

223− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

137+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

224

138

225− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

139+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

226

140

227− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

141+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

228

142

229− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

143+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

230

144

231− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" make"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

145+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" make"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

232

146

233− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" both"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

147+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" both"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

234

148

235− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

149+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

236

150

237− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

151+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

238

152

239− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" replace"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

153+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" replace"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

240

154

241− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

155+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

242

156

243− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

157+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

244

158

245− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

159+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

246

160

247− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" World"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

161+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" World"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

248

162

249− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

163+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

250

164

251− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

165+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

252

166

253− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

167+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

254

168

255− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

169+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

256

170

257− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

171+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

258

172

259− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

173+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

260

174

261− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

175+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

262

176

263− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

177+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

264

178

265− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" add"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

179+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" add"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

266

180

267− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" a"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

181+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" a"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

268

182

269− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

183+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

270

184

271− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" above"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

185+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" above"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

272

186

273− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

187+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

274

188

275− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" fmt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

189+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" fmt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

276

190

277− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":".Println"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

191+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":".Println"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

278

192

279− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":" line"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

193+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":" line"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

280

194

281− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

195+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

282

196

283− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"multiedit","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

197+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.multiedit:0","index":0,"type":"function","function":{"name":"multiedit","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

284

198

285− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

199+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

286

200

287− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

201+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

288

202

289− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

203+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

290

204

291− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

205+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

292

206

293− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

207+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

294

208

295− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

209+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

296

210

297− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

211+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

298

212

299− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

213+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

300

214

301− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

215+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

302

216

303− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

217+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

304

218

305− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

219+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

306

220

307− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

221+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

308

222

309− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

223+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

310

224

311− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

225+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

312

226

313− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

227+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

314

228

315− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

229+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

316

230

317− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

231+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

318

232

319− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"/mult"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

233+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/mult"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

320

234

321− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"ied"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

235+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"ied"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

322

236

323− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"it"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

237+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"it"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

324

238

325− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"_tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

239+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

326

240

327− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"/main"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

241+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/main"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

328

242

329− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":".go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

243+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

330

244

331− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

245+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

332

246

333− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

247+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

334

248

335− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"ed"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

249+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"ed"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

336

250

337− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"its"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

251+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"its"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

338

252

339− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

253+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

340

254

341− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" [{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

255+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" [{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

342

256

343− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"old"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

257+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"old"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

344

258

345− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"_string"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

259+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_string"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

346

260

347− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

261+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

348

262

349− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" \"\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

263+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

350

264

351− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"tf"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

265+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tf"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

352

266

353− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"mt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

267+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"mt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

354

268

355− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":".Println"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

269+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".Println"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

356

270

357− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"(\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

271+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"(\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

358

272

359− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"Hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

273+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

360

274

361− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

275+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

362

276

363− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" World"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

277+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" World"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

364

278

365− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"!\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

279+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"!\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

366

280

367− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\")"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

281+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\")"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

368

282

369− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

283+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

370

284

371− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

285+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

372

286

373− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"new"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

287+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"new"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

374

288

375− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"_string"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

289+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_string"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

376

290

377− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

291+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

378

292

379− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" \"\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

293+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

380

294

381− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"t"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

295+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"t"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

382

296

383− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"//"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

297+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"//"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

384

298

385− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" G"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

299+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" G"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

386

300

387− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"reeting"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

301+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"reeting"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

388

302

389− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\\n"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

303+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\\n"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

390

304

391− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\\t"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

305+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\\t"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

392

306

393− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"fmt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

307+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"fmt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

394

308

395− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":".Println"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

309+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".Println"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

396

310

397− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"(\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

311+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"(\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

398

312

399− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"Hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

313+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

400

314

401− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

315+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

402

316

403− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":" Crush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

317+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" Crush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

404

318

405− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"!\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

319+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"!\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

406

320

407− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\")"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

321+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\")"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

408

322

409− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

323+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

410

324

411− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"","arguments":"]}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

325+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"]}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

412

326

413− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":null}

327+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

414

328

415− data: {"id":"gen-1760329332-lrlq0ls8vALHfDsMMSPz","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329332,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7454,"completion_tokens":109,"total_tokens":7563,"cost":0.0047449,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0044724,"upstream_inference_completions_cost":0.0002725},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

329+ data: {"id":"gen-1761220160-LU2nGVoPutn6Q02vzowr","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220160,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6944,"completion_tokens":110,"total_tokens":7054,"cost":0.0041481,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0038192,"upstream_inference_completions_cost":0.0003289},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

416

330

417 data: [DONE]

331 data: [DONE]

418

332

@@ -421,22 +335,22 @@ interactions:

421 - text/event-stream

335 - text/event-stream

422 status: 200 OK

336 status: 200 OK

423 code: 200

337 code: 200

424− duration: 579.351041ms

338+ duration: 900.6645ms

425- id: 3

339- id: 3

426 request:

340 request:

427 proto: HTTP/1.1

341 proto: HTTP/1.1

428 proto_major: 1

342 proto_major: 1

429 proto_minor: 1

343 proto_minor: 1

430− content_length: 32052

344+ content_length: 31325

431 host: ""

345 host: ""

432− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you make those changes to main.go using multiedit. First, let me check the current content of the file.\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"},{\"content\":\"Now I'll use multiedit to make both changes: replace 'Hello, World!' with 'Hello, Crush!' and add a comment above the fmt.Println line.\",\"tool_calls\":[{\"id\":\"multiedit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\", \\\"edits\\\": [{\\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\", \\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"multiedit:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

346+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you make those changes to main.go using multiedit. Let me first read the file to see its current contents.\",\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"},{\"content\":\"Now I'll use multiedit to make both changes: replace 'Hello, World!' with 'Hello, Crush!' and add a comment above the fmt.Println line.\",\"tool_calls\":[{\"id\":\"functions.multiedit:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\", \\\"edits\\\": [{\\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\", \\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<result>\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\n</result>\\n\",\"tool_call_id\":\"functions.multiedit:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

433 headers:

347 headers:

434 Accept:

348 Accept:

435 - application/json

349 - application/json

436 Content-Type:

350 Content-Type:

437 - application/json

351 - application/json

438 User-Agent:

352 User-Agent:

439− - OpenAI/Go 2.3.0

353+ - OpenAI/Go 2.7.1

440 url: https://openrouter.ai/api/v1/chat/completions

354 url: https://openrouter.ai/api/v1/chat/completions

441 method: POST

355 method: POST

442 response:

356 response:

@@ -445,113 +359,33 @@ interactions:

445 proto_minor: 0

359 proto_minor: 0

446 content_length: -1

360 content_length: -1

447 body: |+

361 body: |+

448− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

362+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

449−

450− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done!"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

451−

452− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" I've"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

453−

454− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

455−

456− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":":\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

457−

458− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

459−

460− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

461−

462− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" Re"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

463−

464− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"placed"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

465−

466− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

467−

468− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

469−

470− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

471−

472− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" World"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

473−

474− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

475−

476− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

477−

478− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

479−

480− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

481−

482− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

483−

484− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

485−

486− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

487−

488− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" \n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

489−

490− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

491−

492− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

493−

494− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" Added"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

495−

496− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

497−

498− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

499−

500− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" '//"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

501−

502− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" G"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

503−

504− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"reeting"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

505−

506− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

507−

508− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" above"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

509−

510− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

511−

512− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" fmt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

513−

514− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":".Println"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

515−

516− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" line"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

517−

518− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

519−

520− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"The"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

521−

522− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

523−

524− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" have"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

525−

526− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" been"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

527−

528− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" applied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

529

363

530− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

364+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

531

365

532− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

366+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":"!"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

533

367

534− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

368+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" The"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

535

369

536− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

370+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

537

371

538− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" a"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

372+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" have"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

539

373

540− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" single"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

374+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" been"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

541

375

542− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

376+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" applied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

543

377

544− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

378+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

545

379

546− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

380+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

547

381

548− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":" operation"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

382+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

549

383

550− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

384+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

551

385

552− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

386+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

553

387

554− data: {"id":"gen-1760329334-blpdvYIgYu0t0G5nk3eI","provider":"Fireworks","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329334,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7610,"completion_tokens":53,"total_tokens":7663,"cost":0.0046985,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.004566,"upstream_inference_completions_cost":0.0001325},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

388+ data: {"id":"gen-1761220163-pY7lkXpF7snLvMpKFTY6","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220163,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7105,"completion_tokens":12,"total_tokens":7117,"cost":0.00279375,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00277095,"upstream_inference_completions_cost":0.0000228},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

555

389

556 data: [DONE]

390 data: [DONE]

557

391

@@ -560,4 +394,4 @@ interactions:

560 - text/event-stream

394 - text/event-stream

561 status: 200 OK

395 status: 200 OK

562 code: 200

396 code: 200

563− duration: 2.087444542s

397+ duration: 10.067079875s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls.yaml+59−104

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,29 +24,21 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

29− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

31− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" ."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":" .go files and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

33− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":" list directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

35− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

37− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":" parallel"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

39− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" list"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""}

41− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

41+ data: {"id":"gen-1761220200-W5HiCtJVYBYfEXqgkSIr","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":160,"completion_tokens":9,"total_tokens":169,"cost":0.0000375,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000024,"upstream_inference_completions_cost":0.0000135},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

42−

43− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

44−

45− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":" parallel"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

46−

47− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

48−

49− data: {"id":"gen-1760329364-SQOxMen8F4JxjnHbwXBH","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":156,"completion_tokens":10,"total_tokens":166,"cost":0.0000384,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000234,"upstream_inference_completions_cost":0.000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

51 data: [DONE]

43 data: [DONE]

@@ -55,22 +47,22 @@ interactions:

55 - text/event-stream

47 - text/event-stream

56 status: 200 OK

48 status: 200 OK

57 code: 200

49 code: 200

58− duration: 1.11080875s

50+ duration: 1.326503083s

59- id: 1

51- id: 1

60 request:

52 request:

61 proto: HTTP/1.1

53 proto: HTTP/1.1

62 proto_major: 1

54 proto_major: 1

63 proto_minor: 1

55 proto_minor: 1

64− content_length: 30836

56+ content_length: 30066

65 host: ""

57 host: ""

66− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

58+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

67 headers:

59 headers:

68 Accept:

60 Accept:

69 - application/json

61 - application/json

70 Content-Type:

62 Content-Type:

71 - application/json

63 - application/json

72 User-Agent:

64 User-Agent:

73− - OpenAI/Go 2.3.0

65+ - OpenAI/Go 2.7.1

74 url: https://openrouter.ai/api/v1/chat/completions

66 url: https://openrouter.ai/api/v1/chat/completions

75 method: POST

67 method: POST

76 response:

68 response:

@@ -79,39 +71,11 @@ interactions:

79 proto_minor: 0

71 proto_minor: 0

80 content_length: -1

72 content_length: -1

81 body: |+

73 body: |+

82− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

74+ data: {"id":"gen-1761220200-NNYKYxF0b61AOH8mJQDg","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

83−

84− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"glob:0","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

85−

86− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

87−

88− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"pattern"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

89−

90− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

91−

92− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"**"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

93−

94− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/*."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

95−

96− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

97−

98− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

99−

100− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"id":"ls:1","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

101−

102− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

103−

104− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"function":{"arguments":"path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

105−

106− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

107

108− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"function":{"arguments":" \".\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

76+ data: {"id":"gen-1761220200-NNYKYxF0b61AOH8mJQDg","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.glob:0","function":{"arguments":"{\"pattern\": \"*.go\"}","name":"glob"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

109

110− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"function":{"arguments":"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

78+ data: {"id":"gen-1761220200-NNYKYxF0b61AOH8mJQDg","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220200,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7484,"completion_tokens":7,"total_tokens":7491,"cost":0.003756,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.003742,"upstream_inference_completions_cost":0.000014},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

111−

112− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

113−

114− data: {"id":"gen-1760329364-9DsfDn3jryGmsexBfzWY","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329364,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7568,"completion_tokens":29,"total_tokens":7597,"cost":0.0046133,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045408,"upstream_inference_completions_cost":0.0000725},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

115

116 data: [DONE]

80 data: [DONE]

117

@@ -120,22 +84,22 @@ interactions:

120 - text/event-stream

84 - text/event-stream

121 status: 200 OK

85 status: 200 OK

122 code: 200

86 code: 200

123− duration: 2.455290875s

87+ duration: 629.792875ms

124- id: 2

88- id: 2

125 request:

89 request:

126 proto: HTTP/1.1

90 proto: HTTP/1.1

127 proto_major: 1

91 proto_major: 1

128 proto_minor: 1

92 proto_minor: 1

129− content_length: 31345

93+ content_length: 30351

130 host: ""

94 host: ""

131− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"ls:1\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/main.go\",\"tool_call_id\":\"glob:0\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

95+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/main.go\",\"tool_call_id\":\"functions.glob:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

132 headers:

96 headers:

133 Accept:

97 Accept:

134 - application/json

98 - application/json

135 Content-Type:

99 Content-Type:

136 - application/json

100 - application/json

137 User-Agent:

101 User-Agent:

138− - OpenAI/Go 2.3.0

102+ - OpenAI/Go 2.7.1

139 url: https://openrouter.ai/api/v1/chat/completions

103 url: https://openrouter.ai/api/v1/chat/completions

140 method: POST

104 method: POST

141 response:

105 response:

@@ -144,61 +108,52 @@ interactions:

144 proto_minor: 0

108 proto_minor: 0

145 content_length: -1

109 content_length: -1

146 body: |+

110 body: |+

147− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

111+ data: {"id":"gen-1761220202-acHreOrVyaJLuf4zH3ls","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220202,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

148−

149− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

150−

151− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

152−

153− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

154−

155− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

156−

157− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

158−

159− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

160−

161− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

162−

163− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

164−

165− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

166−

167− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"`\n\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

168−

169− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"Current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

170−

171− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

172−

173− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" contains"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

174

112

175− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":":\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

113+ data: {"id":"gen-1761220202-acHreOrVyaJLuf4zH3ls","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220202,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.ls:1","index":0,"type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

176

114

177− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

115+ data: {"id":"gen-1761220202-acHreOrVyaJLuf4zH3ls","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220202,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

178

116

179− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

117+ data: {"id":"gen-1761220202-acHreOrVyaJLuf4zH3ls","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220202,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

180

118

181− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

119+ data: {"id":"gen-1761220202-acHreOrVyaJLuf4zH3ls","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220202,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7176,"completion_tokens":12,"total_tokens":7188,"cost":0.007212,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.007176,"upstream_inference_completions_cost":0.000036},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

182

120

183− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":".mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

121+ data: [DONE]

184−

185− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

186−

187− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" \n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

188−

189− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

190−

191− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

192−

193− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

194−

195− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

196

122

197− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

123+ headers:

124+ Content-Type:

125+ - text/event-stream

126+ status: 200 OK

127+ code: 200

128+ duration: 557.386458ms

129+- id: 3

130+ request:

131+ proto: HTTP/1.1

132+ proto_major: 1

133+ proto_minor: 1

134+ content_length: 30633

135+ host: ""

136+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/main.go\",\"tool_call_id\":\"functions.glob:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"functions.ls:1\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"functions.ls:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

137+ headers:

138+ Accept:

139+ - application/json

140+ Content-Type:

141+ - application/json

142+ User-Agent:

143+ - OpenAI/Go 2.7.1

144+ url: https://openrouter.ai/api/v1/chat/completions

145+ method: POST

146+ response:

147+ proto: HTTP/2.0

148+ proto_major: 2

149+ proto_minor: 0

150+ content_length: -1

151+ body: |+

152+ data: {"id":"gen-1761220202-KlYEF7AoDnehDVoBKvyQ","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220203,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

198

153

199− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

154+ data: {"id":"gen-1761220202-KlYEF7AoDnehDVoBKvyQ","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220203,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found 1 Go file: `main.go`\n\nCurrent directory contents:\n- go.mod\n- main.go"},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

200

155

201− data: {"id":"gen-1760329367-2n3m7dTWIQWw97bN78O9","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329368,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7675,"completion_tokens":26,"total_tokens":7701,"cost":0.00467,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.004605,"upstream_inference_completions_cost":0.000065},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

156+ data: {"id":"gen-1761220202-KlYEF7AoDnehDVoBKvyQ","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220203,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6983,"completion_tokens":21,"total_tokens":7004,"cost":0.0035335,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0034915,"upstream_inference_completions_cost":0.000042},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

202

157

203 data: [DONE]

158 data: [DONE]

204

159

@@ -207,4 +162,4 @@ interactions:

207 - text/event-stream

162 - text/event-stream

208 status: 200 OK

163 status: 200 OK

209 code: 200

164 code: 200

210− duration: 2.791088875s

165+ duration: 741.995083ms

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/read_a_file.yaml+59−63

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,19 +24,15 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220108-0EjD4tDrkLa0XzPbiZmz","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":"Read"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220108-0EjD4tDrkLa0XzPbiZmz","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":"Read"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220108-0EjD4tDrkLa0XzPbiZmz","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":" the go mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":" go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220108-0EjD4tDrkLa0XzPbiZmz","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

35− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":" mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220108-0EjD4tDrkLa0XzPbiZmz","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":131,"completion_tokens":5,"total_tokens":136,"cost":0.00002565,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001965,"upstream_inference_completions_cost":0.000006},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

36−

37− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

38−

39− data: {"id":"gen-1760329212-mzKXskgVEJc8QCwQlr0s","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":131,"completion_tokens":5,"total_tokens":136,"cost":0.0000171,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000131,"upstream_inference_completions_cost":0.000004},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

41 data: [DONE]

37 data: [DONE]

@@ -45,22 +41,22 @@ interactions:

45 - text/event-stream

41 - text/event-stream

46 status: 200 OK

42 status: 200 OK

47 code: 200

43 code: 200

48− duration: 1.613377333s

44+ duration: 848.267167ms

49- id: 1

45- id: 1

50 request:

46 request:

51 proto: HTTP/1.1

47 proto: HTTP/1.1

52 proto_major: 1

48 proto_major: 1

53 proto_minor: 1

49 proto_minor: 1

54− content_length: 30709

50+ content_length: 29939

55 host: ""

51 host: ""

56− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

52+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Read the go mod\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

57 headers:

53 headers:

58 Accept:

54 Accept:

59 - application/json

55 - application/json

60 Content-Type:

56 Content-Type:

61 - application/json

57 - application/json

62 User-Agent:

58 User-Agent:

63− - OpenAI/Go 2.3.0

59+ - OpenAI/Go 2.7.1

64 url: https://openrouter.ai/api/v1/chat/completions

60 url: https://openrouter.ai/api/v1/chat/completions

65 method: POST

61 method: POST

66 response:

62 response:

@@ -69,59 +65,59 @@ interactions:

69 proto_minor: 0

65 proto_minor: 0

70 content_length: -1

66 content_length: -1

71 body: |+

67 body: |+

72− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

68+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.view:0","index":0,"type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

70+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.view:0","index":0,"type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

72+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

74+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

100− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

102− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

103

104− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

100+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

105

101

106− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

102+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

107

103

108− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

104+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

109

105

110− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/read"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

106+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/read"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

111

107

112− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

108+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

113

109

114− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

110+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

115

111

116− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

112+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

117

113

118− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".mod"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

114+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".mod"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

119

115

120− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

116+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

121

117

122− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

118+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

123

119

124− data: {"id":"gen-1760329212-7dye7IaW1b8SR6XD3kcG","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329212,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6885,"completion_tokens":34,"total_tokens":6919,"cost":0.00274975,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00268515,"upstream_inference_completions_cost":0.0000646},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

120+ data: {"id":"gen-1761220108-B6pksThILk4jIPez3nv5","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220108,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6786,"completion_tokens":34,"total_tokens":6820,"cost":0.0041566,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0040716,"upstream_inference_completions_cost":0.000085},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

125

121

126 data: [DONE]

122 data: [DONE]

127

123

@@ -130,22 +126,22 @@ interactions:

130 - text/event-stream

126 - text/event-stream

131 status: 200 OK

127 status: 200 OK

132 code: 200

128 code: 200

133− duration: 2.214002417s

129+ duration: 957.780292ms

134- id: 2

130- id: 2

135 request:

131 request:

136 proto: HTTP/1.1

132 proto: HTTP/1.1

137 proto_major: 1

133 proto_major: 1

138 proto_minor: 1

134 proto_minor: 1

139− content_length: 31063

135+ content_length: 30294

140 host: ""

136 host: ""

141− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

137+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

142 headers:

138 headers:

143 Accept:

139 Accept:

144 - application/json

140 - application/json

145 Content-Type:

141 Content-Type:

146 - application/json

142 - application/json

147 User-Agent:

143 User-Agent:

148− - OpenAI/Go 2.3.0

144+ - OpenAI/Go 2.7.1

149 url: https://openrouter.ai/api/v1/chat/completions

145 url: https://openrouter.ai/api/v1/chat/completions

150 method: POST

146 method: POST

151 response:

147 response:

@@ -154,39 +150,39 @@ interactions:

154 proto_minor: 0

150 proto_minor: 0

155 content_length: -1

151 content_length: -1

156 body: |+

152 body: |+

157− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

153+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

158

154

159− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"```\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

155+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"Module"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

160

156

161− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"module"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

157+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

162

158

163− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":" example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

159+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":" example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

164

160

165− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":".com"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

161+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":".com"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

166

162

167− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"/test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

163+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"/test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

168

164

169− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"project"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

165+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"project"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

170

166

171− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

167+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":" \n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

172

168

173− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

169+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

174

170

175− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

171+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":" version"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

176

172

177− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

173+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

178

174

179− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

175+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

180

176

181− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"23"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

177+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

182

178

183− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

179+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

184

180

185− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":"```"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

181+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":"23"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

186

182

187− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

183+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

188

184

189− data: {"id":"gen-1760329215-L1zsNGnncXONFeFHw3Nj","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329215,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6963,"completion_tokens":15,"total_tokens":6978,"cost":0.0042153,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0041778,"upstream_inference_completions_cost":0.0000375},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

185+ data: {"id":"gen-1761220109-dSYhAmctHxTEXpEE3VzB","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220109,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6864,"completion_tokens":15,"total_tokens":6879,"cost":0.00270546,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00267696,"upstream_inference_completions_cost":0.0000285},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

190

186

191 data: [DONE]

187 data: [DONE]

192

188

@@ -195,4 +191,4 @@ interactions:

195 - text/event-stream

191 - text/event-stream

196 status: 200 OK

192 status: 200 OK

197 code: 200

193 code: 200

198− duration: 1.479381667s

194+ duration: 2.810485583s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/simple_test.yaml+15−15

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,13 +24,13 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329210-e4kcGOor2VN4UHPDvlMV","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220102-lAH9RiaVfSeyDpWZLKK8","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220102,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329210-e4kcGOor2VN4UHPDvlMV","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220102-lAH9RiaVfSeyDpWZLKK8","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220102,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329210-e4kcGOor2VN4UHPDvlMV","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

31+ data: {"id":"gen-1761220102-lAH9RiaVfSeyDpWZLKK8","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220102,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

33− data: {"id":"gen-1760329210-e4kcGOor2VN4UHPDvlMV","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":128,"completion_tokens":2,"total_tokens":130,"cost":0.0000222,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000192,"upstream_inference_completions_cost":0.000003},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

33+ data: {"id":"gen-1761220102-lAH9RiaVfSeyDpWZLKK8","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220102,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":128,"completion_tokens":2,"total_tokens":130,"cost":0.0000222,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000192,"upstream_inference_completions_cost":0.000003},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

35 data: [DONE]

@@ -39,22 +39,22 @@ interactions:

39 - text/event-stream

40 status: 200 OK

41 code: 200

42− duration: 1.701398916s

42+ duration: 945.429916ms

43- id: 1

44 request:

45 proto: HTTP/1.1

46 proto_major: 1

47 proto_minor: 1

48− content_length: 30699

48+ content_length: 29929

49 host: ""

50− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/simple_test\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

50+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Hello\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

51 headers:

52 Accept:

53 - application/json

54 Content-Type:

55 - application/json

56 User-Agent:

57− - OpenAI/Go 2.3.0

57+ - OpenAI/Go 2.7.1

58 url: https://openrouter.ai/api/v1/chat/completions

59 method: POST

60 response:

@@ -63,15 +63,15 @@ interactions:

63 proto_minor: 0

64 content_length: -1

65 body: |+

66− data: {"id":"gen-1760329210-UIc25PhEYaEFzjCopuHo","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

66+ data: {"id":"gen-1761220102-X6GOhnHvFNCvGA4GyPy1","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220103,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

68− data: {"id":"gen-1760329210-UIc25PhEYaEFzjCopuHo","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

68+ data: {"id":"gen-1761220102-X6GOhnHvFNCvGA4GyPy1","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220103,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hey"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

70− data: {"id":"gen-1760329210-UIc25PhEYaEFzjCopuHo","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

70+ data: {"id":"gen-1761220102-X6GOhnHvFNCvGA4GyPy1","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220103,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

72− data: {"id":"gen-1760329210-UIc25PhEYaEFzjCopuHo","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

72+ data: {"id":"gen-1761220102-X6GOhnHvFNCvGA4GyPy1","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220103,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

74− data: {"id":"gen-1760329210-UIc25PhEYaEFzjCopuHo","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329210,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7538,"completion_tokens":3,"total_tokens":7541,"cost":0.0045303,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045228,"upstream_inference_completions_cost":0.0000075},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

74+ data: {"id":"gen-1761220102-X6GOhnHvFNCvGA4GyPy1","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220103,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6782,"completion_tokens":3,"total_tokens":6785,"cost":0.00265068,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00264498,"upstream_inference_completions_cost":0.0000057},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

76 data: [DONE]

@@ -80,4 +80,4 @@ interactions:

80 - text/event-stream

81 status: 200 OK

82 code: 200

83− duration: 2.436602s

83+ duration: 6.097041958s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool.yaml+53−63

@@ -6,16 +6,16 @@ interactions:

6 proto: HTTP/1.1

7 proto_major: 1

8 proto_minor: 1

9− content_length: 769

9+ content_length: 29989

10 host: ""

11− body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n<rules>\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse sourcegraph to search for ''func main'' in Go repositories\n <think>\n\n</think>","role":"user"}],"model":"qwen/qwen3-next-80b-a3b-instruct","max_tokens":40,"stream_options":{"include_usage":true},"usage":{"include":true},"stream":true}'

11+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

12 headers:

13 Accept:

14 - application/json

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,21 +24,11 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

27+ data: {"id":"gen-1761220176-hQWMQJT75aYKMrIpNzfr","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

28−

29− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

30−

31− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":" for func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

32−

33− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":" main in Go repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

35− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":" using Source"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

29+ data: {"id":"gen-1761220176-hQWMQJT75aYKMrIpNzfr","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.sourcegraph:0","function":{"arguments":"{\"query\": \"func main lang:go\", \"timeout\": 30}","name":"sourcegraph"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

37− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":"graph"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

31+ data: {"id":"gen-1761220176-hQWMQJT75aYKMrIpNzfr","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7464,"completion_tokens":15,"total_tokens":7479,"cost":0.003762,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.003732,"upstream_inference_completions_cost":0.00003},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

38−

39− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""}

40−

41− data: {"id":"gen-1760329336-7qhCEEQC5O5Y3Bc2x9W7","provider":"SiliconFlow","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":140,"completion_tokens":11,"total_tokens":151,"cost":0.000035,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000196,"upstream_inference_completions_cost":0.0000154},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

43 data: [DONE]

33 data: [DONE]

@@ -47,22 +37,22 @@ interactions:

47 - text/event-stream

37 - text/event-stream

48 status: 200 OK

38 status: 200 OK

49 code: 200

39 code: 200

50− duration: 1.835886417s

40+ duration: 621.638291ms

51- id: 1

41- id: 1

52 request:

42 request:

53 proto: HTTP/1.1

43 proto: HTTP/1.1

54 proto_major: 1

44 proto_major: 1

55 proto_minor: 1

45 proto_minor: 1

56− content_length: 30759

46+ content_length: 769

57 host: ""

47 host: ""

58− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

48+ body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n<rules>\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nuse sourcegraph to search for ''func main'' in Go repositories\n <think>\n\n</think>","role":"user"}],"model":"qwen/qwen3-next-80b-a3b-instruct","max_tokens":40,"stream_options":{"include_usage":true},"usage":{"include":true},"stream":true}'

59 headers:

49 headers:

60 Accept:

50 Accept:

61 - application/json

51 - application/json

62 Content-Type:

52 Content-Type:

63 - application/json

53 - application/json

64 User-Agent:

54 User-Agent:

65− - OpenAI/Go 2.3.0

55+ - OpenAI/Go 2.7.1

66 url: https://openrouter.ai/api/v1/chat/completions

56 url: https://openrouter.ai/api/v1/chat/completions

67 method: POST

57 method: POST

68 response:

58 response:

@@ -71,45 +61,19 @@ interactions:

71 proto_minor: 0

61 proto_minor: 0

72 content_length: -1

62 content_length: -1

73 body: |+

63 body: |+

74− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

64+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

75−

76− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"sourcegraph:0","type":"function","function":{"name":"sourcegraph"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

77−

78− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

79−

80− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"query"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

81−

82− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

83−

84− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

85−

86− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"func"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

87−

88− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

89−

90− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" lang"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

91−

92− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

94− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

66+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

96− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

68+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":" for func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

98− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

70+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":" main in Go repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

100− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"count"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

72+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":" using Sourcegraph"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

101

102− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

74+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":null}

103

104− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

76+ data: {"id":"gen-1761220176-C539TimwBBkELBXM2Jvu","provider":"Alibaba","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220176,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":144,"completion_tokens":10,"total_tokens":154,"cost":0.000092,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000072,"upstream_inference_completions_cost":0.00002},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

105−

106− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"10"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

107−

108− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

109−

110− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

111−

112− data: {"id":"gen-1760329336-uDTGfn5r6jFVITeXINKZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329349,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7551,"completion_tokens":26,"total_tokens":7577,"cost":0.0045956,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045306,"upstream_inference_completions_cost":0.000065},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

113

114 data: [DONE]

78 data: [DONE]

115

@@ -118,7 +82,7 @@ interactions:

118 - text/event-stream

82 - text/event-stream

119 status: 200 OK

83 status: 200 OK

120 code: 200

84 code: 200

121− duration: 10.173527333s

85+ duration: 1.587788291s

122- id: 2

86- id: 2

123 request:

87 request:

124 proto: HTTP/1.1

88 proto: HTTP/1.1

@@ -140,28 +104,28 @@ interactions:

140 proto_minor: 0

104 proto_minor: 0

141 content_length: -1

105 content_length: -1

142 uncompressed: true

106 uncompressed: true

143− body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/pingguoxueyuan/gostudy"},"file":{"path":"listen15/defer/main.go","url":"/github.com/pingguoxueyuan/gostudy/-/blob/listen15/defer/main.go","content":"package main\n\nimport (\n\t\"fmt\"\n)\n\nfunc funcA() int {\n\tx := 5\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn x\n}\n\nfunc funcB() (x int) {\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn 5\n}\n\nfunc funcC() (y int) {\n\tx := 5\n\tdefer func() {\n\t\tx += 1\n\t}()\n\treturn x\n}\n\nfunc funcD() (x int) {\n\tdefer func(x int) {\n\t\tx += 1\n\t}(x)\n\treturn 5\n}\n\nfunc main() {\n\t//fmt.Println(funcA())\n\t//fmt.Println(funcB())\n\t//fmt.Println(funcC())\n\tfmt.Println(funcD())\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":36,"offsetAndLengths":[[0,9]]},{"preview":"\t//fmt.Println(funcA())","lineNumber":37,"offsetAndLengths":[[15,4]]},{"preview":"\t//fmt.Println(funcB())","lineNumber":38,"offsetAndLengths":[[15,4]]},{"preview":"\t//fmt.Println(funcC())","lineNumber":39,"offsetAndLengths":[[15,4]]},{"preview":"\tfmt.Println(funcD())","lineNumber":40,"offsetAndLengths":[[13,4]]},{"preview":"func funcA() int {","lineNumber":6,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":8,"offsetAndLengths":[[7,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func funcB() (x int) {","lineNumber":14,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":15,"offsetAndLengths":[[7,4]]},{"preview":"func funcC() (y int) {","lineNumber":21,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func() {","lineNumber":23,"offsetAndLengths":[[7,4]]},{"preview":"func funcD() (x int) {","lineNumber":29,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tdefer func(x int) {","lineNumber":30,"offsetAndLengths":[[7,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/Zhouchaowen/golang-tutorial"},"file":{"path":"12-library/8-error/ch_1/main.go","url":"/github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go","content":"package main\n\nimport (\n\t\"errors\"\n\t\"fmt\"\n)\n\nfunc func1() error {\n\treturn errors.New(\"func1 error\")\n}\n\nfunc func2() error {\n\treturn fmt.Errorf(\"func2 error: %w\", func1())\n}\n\nfunc main() {\n\terr := func2()\n\tif err != nil {\n\t\tfmt.Println(err)\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":15,"offsetAndLengths":[[0,9]]},{"preview":"\terr := func2()","lineNumber":16,"offsetAndLengths":[[8,4]]},{"preview":"func func1() error {","lineNumber":7,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\treturn errors.New(\"func1 error\")","lineNumber":8,"offsetAndLengths":[[20,4]]},{"preview":"func func2() error {","lineNumber":11,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\treturn fmt.Errorf(\"func2 error: %w\", func1())","lineNumber":12,"offsetAndLengths":[[20,4],[38,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/lynda"},"file":{"path":"cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go","url":"/github.com/GoesToEleven/lynda/-/blob/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc greeting() {\n\tfmt.Println(\"Hello world!\")\n}\n\nfunc main() {\n\tgreeting()\n}\n\n/*\nAll material is licensed under the Apache License Version 2.0, January 2004\nhttp://www.apache.org/licenses/LICENSE-2.0\n*/\n"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]}]}}}}'

107+ body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":33,"offsetAndLengths":[[0,9]]},{"preview":"\tFuncA()","lineNumber":34,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncB()","lineNumber":35,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncC()","lineNumber":36,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncD()","lineNumber":37,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncE()","lineNumber":38,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncF()","lineNumber":39,"offsetAndLengths":[[1,4]]},{"preview":"func FuncE() {","lineNumber":4,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncE\")","lineNumber":5,"offsetAndLengths":[[14,4]]},{"preview":"func FuncD() {","lineNumber":8,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncE()","lineNumber":9,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncD\")","lineNumber":10,"offsetAndLengths":[[14,4]]},{"preview":"func FuncC() {","lineNumber":13,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncD()","lineNumber":14,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncC\")","lineNumber":15,"offsetAndLengths":[[14,4]]},{"preview":"func FuncB() {","lineNumber":18,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncC()","lineNumber":19,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncB\")","lineNumber":20,"offsetAndLengths":[[14,4]]},{"preview":"func FuncA() {","lineNumber":23,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncB()","lineNumber":24,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncA\")","lineNumber":25,"offsetAndLengths":[[14,4]]},{"preview":"func FuncF() {","lineNumber":28,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncF\")","lineNumber":29,"offsetAndLengths":[[14,4]]},{"preview":"\tFuncE()","lineNumber":30,"offsetAndLengths":[[1,4]]}]}]}}}}'

144 headers:

108 headers:

145 Content-Type:

109 Content-Type:

146 - application/json

110 - application/json

147 status: 200 OK

111 status: 200 OK

148 code: 200

112 code: 200

149− duration: 1.337772458s

113+ duration: 1.473759417s

150- id: 3

114- id: 3

151 request:

115 request:

152 proto: HTTP/1.1

116 proto: HTTP/1.1

153 proto_major: 1

117 proto_major: 1

154 proto_minor: 1

118 proto_minor: 1

155− content_length: 38781

119+ content_length: 37787

156 host: ""

120 host: ""

157− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"sourcegraph:0\",\"function\":{\"arguments\":\"{\\\"query\\\": \\\"func main lang:go\\\", \\\"count\\\": 10}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/pingguoxueyuan/gostudy/listen15/defer/main.go\\n\\nURL: /github.com/pingguoxueyuan/gostudy/-/blob/listen15/defer/main.go\\n\\n```\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| func main() {\\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| \\t//fmt.Println(funcA())\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcB())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcC())\\n40| \\t//fmt.Println(funcC())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\tfmt.Println(funcD())\\n41| \\tfmt.Println(funcD())\\n42| }\\n43| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| func funcA() int {\\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tdefer func() {\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n```\\n\\n```\\n4| \\t\\\"fmt\\\"\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| func funcB() (x int) {\\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n```\\n\\n```\\n5| )\\n6| \\n7| func funcA() int {\\n8| \\tx := 5\\n9| \\tdefer func() {\\n10| \\t\\tx += 1\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| \\tdefer func() {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n```\\n\\n```\\n11| \\t}()\\n12| \\treturn x\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| func funcC() (y int) {\\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n```\\n\\n```\\n13| }\\n14| \\n15| func funcB() (x int) {\\n16| \\tdefer func() {\\n17| \\t\\tx += 1\\n18| \\t}()\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tdefer func() {\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n```\\n\\n```\\n19| \\treturn 5\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| func funcD() (x int) {\\n30| func funcD() (x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n```\\n\\n```\\n20| }\\n21| \\n22| func funcC() (y int) {\\n23| \\tx := 5\\n24| \\tdefer func() {\\n25| \\t\\tx += 1\\n26| \\t}()\\n27| \\treturn x\\n28| }\\n29| \\n30| \\tdefer func(x int) {\\n31| \\tdefer func(x int) {\\n32| \\t\\tx += 1\\n33| \\t}(x)\\n34| \\treturn 5\\n35| }\\n36| \\n37| func main() {\\n38| \\t//fmt.Println(funcA())\\n39| \\t//fmt.Println(funcB())\\n40| \\t//fmt.Println(funcC())\\n```\\n\\n## Result 2: github.com/Zhouchaowen/golang-tutorial/12-library/8-error/ch_1/main.go\\n\\nURL: /github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go\\n\\n```\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| func main() {\\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| \\terr := func2()\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| func func1() error {\\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| \\treturn errors.New(\\\"func1 error\\\")\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| func func2() error {\\n12| func func2() error {\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n```\\n\\n```\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n11| \\n12| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n13| \\treturn fmt.Errorf(\\\"func2 error: %w\\\", func1())\\n14| }\\n15| \\n16| func main() {\\n17| \\terr := func2()\\n18| \\tif err != nil {\\n19| \\t\\tfmt.Println(err)\\n20| \\t}\\n21| }\\n22| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import (\\n4| \\t\\\"errors\\\"\\n5| \\t\\\"fmt\\\"\\n6| )\\n7| \\n8| func func1() error {\\n9| \\treturn errors.New(\\\"func1 error\\\")\\n10| }\\n```\\n\\n## Result 3: github.com/GoesToEleven/lynda/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/lynda/-/blob/cc/00_language-fundamentals/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| func main() {\\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n13| /*\\n14| All material is licensed under the Apache License Version 2.0, January 2004\\n15| http://www.apache.org/licenses/LICENSE-2.0\\n16| */\\n17| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n```\\n\\n\",\"tool_call_id\":\"sourcegraph:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

121+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.sourcegraph:0\",\"function\":{\"arguments\":\"{\\\"query\\\": \\\"func main lang:go\\\", \\\"timeout\\\": 30}\",\"name\":\"sourcegraph\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n```\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| \\tFuncB()\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n```\\n\\n```\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tfmt.Println(\\\"FuncA\\\")\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n```\\n\\n```\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| func FuncF() {\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n```\\n\\n```\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| \\tfmt.Println(\\\"FuncF\\\")\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n```\\n\\n```\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tFuncE()\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n```\\n\\n\",\"tool_call_id\":\"functions.sourcegraph:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

158 headers:

122 headers:

159 Accept:

123 Accept:

160 - application/json

124 - application/json

161 Content-Type:

125 Content-Type:

162 - application/json

126 - application/json

163 User-Agent:

127 User-Agent:

164− - OpenAI/Go 2.3.0

128+ - OpenAI/Go 2.7.1

165 url: https://openrouter.ai/api/v1/chat/completions

129 url: https://openrouter.ai/api/v1/chat/completions

166 method: POST

130 method: POST

167 response:

131 response:

@@ -170,11 +134,37 @@ interactions:

170 proto_minor: 0

134 proto_minor: 0

171 content_length: -1

135 content_length: -1

172 body: |+

136 body: |+

173− data: {"id":"gen-1760329354-o8TfcYFLWQgA8iGF1LKy","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329354,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

137+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

138+

139+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

140+

141+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

142+

143+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":"30"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

144+

145+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" matches"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

146+

147+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

148+

149+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

150+

151+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":"func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

152+

153+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

154+

155+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

156+

157+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

158+

159+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

160+

161+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":" repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

162+

163+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

174

164

175− data: {"id":"gen-1760329354-o8TfcYFLWQgA8iGF1LKy","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329354,"choices":[{"index":0,"delta":{"role":"assistant","content":"I found 30 Go repositories containing `func main`. The results show various examples including:\n\n1. **github.com/pingguoxueyuan/gostudy** - A study project with defer examples\n2. **github.com/Zhouchaowen/golang-tutorial** - Tutorial code with error handling examples \n3. **github.com/GoesToEleven/lynda** - Function expression examples\n\nThe code shows different Go patterns like defer usage, error handling, and basic function structure."},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

165+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

176

166

177− data: {"id":"gen-1760329354-o8TfcYFLWQgA8iGF1LKy","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329354,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10110,"completion_tokens":100,"total_tokens":10210,"cost":0.005255,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.005055,"upstream_inference_completions_cost":0.0002},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

167+ data: {"id":"gen-1761220178-WtqDOT0gHmKlmZq9lgiE","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220179,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":9625,"completion_tokens":14,"total_tokens":9639,"cost":0.00378035,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00375375,"upstream_inference_completions_cost":0.0000266},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

178

168

179 data: [DONE]

169 data: [DONE]

180

170

@@ -183,4 +173,4 @@ interactions:

183 - text/event-stream

173 - text/event-stream

184 status: 200 OK

174 status: 200 OK

185 code: 200

175 code: 200

186− duration: 505.068541ms

176+ duration: 3.359791375s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/update_a_file.yaml+73−213

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,21 +24,21 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

27+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":"Update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":"Update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" main.go to print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" main.go to print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" from crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" from crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

39− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

39+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

41− data: {"id":"gen-1760329217-DTBtITEhBYmpCYMM5hNt","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.00002964,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001974,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

41+ data: {"id":"gen-1761220113-Wrx6uMbFFu3R2urMKV6Z","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.00002964,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001974,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

43 data: [DONE]

@@ -47,22 +47,22 @@ interactions:

47 - text/event-stream

48 status: 200 OK

49 code: 200

50− duration: 891.718ms

50+ duration: 624.237417ms

51- id: 1

52 request:

53 proto: HTTP/1.1

54 proto_major: 1

55 proto_minor: 1

56− content_length: 30765

56+ content_length: 29995

57 host: ""

58− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

58+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

59 headers:

60 Accept:

61 - application/json

62 Content-Type:

63 - application/json

64 User-Agent:

65− - OpenAI/Go 2.3.0

65+ - OpenAI/Go 2.7.1

66 url: https://openrouter.ai/api/v1/chat/completions

67 method: POST

68 response:

@@ -71,97 +71,95 @@ interactions:

71 proto_minor: 0

72 content_length: -1

73 body: |+

74− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

74+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

76− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":"I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

76+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":"I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

78− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

78+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

80− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

80+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

82− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

82+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

84− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

84+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

86− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

86+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

88− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

88+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

90− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" change"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

90+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" change"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

92− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

92+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

94− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

94+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

96− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" statement"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

96+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" statement"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

98− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

98+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

100− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" say"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

100+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" say"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

101

102− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

102+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

103

104− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":"hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

104+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":"hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

105

106− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

106+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

107

108− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":" crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

108+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":" crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

109

110− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":"\"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

110+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":"\"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

111

112− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:0","type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

112+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.view:0","index":0,"type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

113

114− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

114+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

115

116− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

116+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

117

118− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

118+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

119

120− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

120+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

121

122− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

122+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

123

124− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

124+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

125

126− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

126+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

127

128− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

128+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

129

130− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

130+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

131

132− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

132+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

133

134− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

134+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

135

136− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

136+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

137

138− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

138+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

139

140− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

140+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

141

142− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

142+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

143

144− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

144+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

145

146− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

146+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

147

148− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

148+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/update"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

149

150− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/update"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

150+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

151

152− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_a"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

152+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

153

154− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

154+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/main"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

155

156− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

156+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

157

158− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

158+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

159

160− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

160+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

161

162− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

162+ data: {"id":"gen-1761220113-apLixMr8FGr5Ev9pzoOA","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220113,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6796,"completion_tokens":52,"total_tokens":6848,"cost":0.00389328,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0037378,"upstream_inference_completions_cost":0.00015548},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

163−

164− data: {"id":"gen-1760329217-IXTrjmNhomrhi72kplLU","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329217,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7552,"completion_tokens":51,"total_tokens":7603,"cost":0.0046587,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045312,"upstream_inference_completions_cost":0.0001275},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

165

163

166 data: [DONE]

164 data: [DONE]

167

165

@@ -170,22 +168,22 @@ interactions:

170 - text/event-stream

168 - text/event-stream

171 status: 200 OK

169 status: 200 OK

172 code: 200

170 code: 200

173− duration: 2.302985625s

171+ duration: 1.70994525s

174- id: 2

172- id: 2

175 request:

173 request:

176 proto: HTTP/1.1

174 proto: HTTP/1.1

177 proto_major: 1

175 proto_major: 1

178 proto_minor: 1

176 proto_minor: 1

179− content_length: 31274

177+ content_length: 30524

180 host: ""

178 host: ""

181− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"I'll update the main.go file to change the print statement to say \\\"hello from crush\\\".\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

179+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"I'll update the main.go file to change the print statement to say \\\"hello from crush\\\".\",\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

182 headers:

180 headers:

183 Accept:

181 Accept:

184 - application/json

182 - application/json

185 Content-Type:

183 Content-Type:

186 - application/json

184 - application/json

187 User-Agent:

185 User-Agent:

188− - OpenAI/Go 2.3.0

186+ - OpenAI/Go 2.7.1

189 url: https://openrouter.ai/api/v1/chat/completions

187 url: https://openrouter.ai/api/v1/chat/completions

190 method: POST

188 method: POST

191 response:

189 response:

@@ -194,115 +192,11 @@ interactions:

194 proto_minor: 0

192 proto_minor: 0

195 content_length: -1

193 content_length: -1

196 body: |+

194 body: |+

197− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"edit","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

195+ data: {"id":"gen-1761220116-MbBlCYI3Ib7M68BgQ1xG","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220116,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

198−

199− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

200−

201− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

202−

203− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

204−

205− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

206−

207− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

208−

209− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

210−

211− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

212−

213− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

214−

215− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

216−

217− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

218−

219− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

220−

221− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

222−

223− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

224−

225− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

226−

227− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

228−

229− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

230−

231− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

232−

233− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"/update"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

234−

235− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

236−

237− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

238−

239− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"/main"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

240−

241− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":".go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

242−

243− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

244−

245− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

246−

247− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"old"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

248−

249− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"_string"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

250−

251− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

252−

253− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" \"\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

254−

255− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"tf"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

256−

257− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"mt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

258−

259− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":".Println"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

260−

261− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"(\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

262−

263− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"Hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

264−

265− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

266

196

267− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" World"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

197+ data: {"id":"gen-1761220116-MbBlCYI3Ib7M68BgQ1xG","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220116,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.edit:1","function":{"arguments":"{\"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\", \"new_string\": \"\\tfmt.Println(\\\"hello from crush\\\")\", \"old_string\": \"\\tfmt.Println(\\\"Hello, World!\\\")\"}","name":"edit"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

268

198

269− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"!\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

199+ data: {"id":"gen-1761220116-MbBlCYI3Ib7M68BgQ1xG","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220116,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7558,"completion_tokens":50,"total_tokens":7608,"cost":0.003879,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.003779,"upstream_inference_completions_cost":0.0001},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

270−

271− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\")"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

272−

273− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

274−

275− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

276−

277− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"new"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

278−

279− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"_string"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

280−

281− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

282−

283− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" \"\\"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

284−

285− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"tf"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

286−

287− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"mt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

288−

289− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":".Println"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

290−

291− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"(\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

292−

293− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

294−

295− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" from"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

296−

297− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":" crush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

298−

299− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\\\")"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

300−

301− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"","arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null}

302−

303− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":null}

304−

305− data: {"id":"gen-1760329221-Mb5Hgsg8ch74BB3FOWss","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329234,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7425,"completion_tokens":62,"total_tokens":7487,"cost":0.00461,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.004455,"upstream_inference_completions_cost":0.000155},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

306

200

307 data: [DONE]

201 data: [DONE]

308

202

@@ -311,22 +205,22 @@ interactions:

311 - text/event-stream

205 - text/event-stream

312 status: 200 OK

206 status: 200 OK

313 code: 200

207 code: 200

314− duration: 10.064114916s

208+ duration: 563.736458ms

315- id: 3

209- id: 3

316 request:

210 request:

317 proto: HTTP/1.1

211 proto: HTTP/1.1

318 proto_major: 1

212 proto_major: 1

319 proto_minor: 1

213 proto_minor: 1

320− content_length: 31772

214+ content_length: 31042

321 host: ""

215 host: ""

322− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"I'll update the main.go file to change the print statement to say \\\"hello from crush\\\".\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"edit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"edit:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

216+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"I'll update the main.go file to change the print statement to say \\\"hello from crush\\\".\",\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n</file>\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"functions.edit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"functions.edit:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

323 headers:

217 headers:

324 Accept:

218 Accept:

325 - application/json

219 - application/json

326 Content-Type:

220 Content-Type:

327 - application/json

221 - application/json

328 User-Agent:

222 User-Agent:

329− - OpenAI/Go 2.3.0

223+ - OpenAI/Go 2.7.1

330 url: https://openrouter.ai/api/v1/chat/completions

224 url: https://openrouter.ai/api/v1/chat/completions

331 method: POST

225 method: POST

332 response:

226 response:

@@ -335,45 +229,11 @@ interactions:

335 proto_minor: 0

229 proto_minor: 0

336 content_length: -1

230 content_length: -1

337 body: |+

231 body: |+

338− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

232+ data: {"id":"gen-1761220119-1hhXvYSZqfvdqKqwAX8t","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220119,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

339−

340− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":"Updated"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

341−

342− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

343−

344− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

345−

346− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

347−

348− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

349−

350− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

351−

352− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":"hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

353−

354− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

355−

356− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

357−

358− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":"\""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

359−

360− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" instead"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

361−

362− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" of"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

363−

364− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

365−

366− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

367−

368− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

369−

370− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":" World"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

371−

372− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":"!\""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

373

233

374− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

234+ data: {"id":"gen-1761220119-1hhXvYSZqfvdqKqwAX8t","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220119,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done. The main.go file has been updated to print \"hello from crush\" instead of \"Hello, World!\"."},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

375

235

376− data: {"id":"gen-1760329235-bdXtbTFwYx7UZucXrEOc","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329235,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7119,"completion_tokens":18,"total_tokens":7137,"cost":0.00281061,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00277641,"upstream_inference_completions_cost":0.0000342},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

236+ data: {"id":"gen-1761220119-1hhXvYSZqfvdqKqwAX8t","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220119,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7087,"completion_tokens":24,"total_tokens":7111,"cost":0.0035915,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0035435,"upstream_inference_completions_cost":0.000048},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

377

237

378 data: [DONE]

238 data: [DONE]

379

239

@@ -382,4 +242,4 @@ interactions:

382 - text/event-stream

242 - text/event-stream

383 status: 200 OK

243 status: 200 OK

384 code: 200

244 code: 200

385− duration: 1.569295792s

245+ duration: 1.0650975s

internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/write_tool.yaml+42−104

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://openrouter.ai/api/v1/chat/completions

20 method: POST

21 response:

@@ -24,17 +24,27 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"gen-1760329358-ns2tlYhnClqvlEd7QFZF","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329358,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

27+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

29− data: {"id":"gen-1760329358-ns2tlYhnClqvlEd7QFZF","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329358,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

29+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

31− data: {"id":"gen-1760329358-ns2tlYhnClqvlEd7QFZF","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329358,"choices":[{"index":0,"delta":{"role":"assistant","content":" config.json with name"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

31+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":" config"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

33− data: {"id":"gen-1760329358-ns2tlYhnClqvlEd7QFZF","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329358,"choices":[{"index":0,"delta":{"role":"assistant","content":" and version data"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""}

33+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":".json"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

35− data: {"id":"gen-1760329358-ns2tlYhnClqvlEd7QFZF","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329358,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""}

35+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

37− data: {"id":"gen-1760329358-ns2tlYhnClqvlEd7QFZF","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1760329358,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":159,"completion_tokens":8,"total_tokens":167,"cost":0.00003585,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002385,"upstream_inference_completions_cost":0.000012},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

37+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":" name"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

38+

39+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

40+

41+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":" version"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

42+

43+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":" data"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

44+

45+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

46+

47+ data: {"id":"gen-1761220182-Ly7xf4NcMn3U6zGvTjEY","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761220182,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":155,"completion_tokens":9,"total_tokens":164,"cost":0.0000227,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000155,"upstream_inference_completions_cost":0.0000072},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

39 data: [DONE]

49 data: [DONE]

@@ -43,22 +53,22 @@ interactions:

43 - text/event-stream

53 - text/event-stream

44 status: 200 OK

54 status: 200 OK

45 code: 200

55 code: 200

46− duration: 956.3445ms

56+ duration: 727.070833ms

47- id: 1

57- id: 1

48 request:

58 request:

49 proto: HTTP/1.1

59 proto: HTTP/1.1

50 proto_major: 1

60 proto_major: 1

51 proto_minor: 1

61 proto_minor: 1

52− content_length: 30802

62+ content_length: 30032

53 host: ""

63 host: ""

54− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

64+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

55 headers:

65 headers:

56 Accept:

66 Accept:

57 - application/json

67 - application/json

58 Content-Type:

68 Content-Type:

59 - application/json

69 - application/json

60 User-Agent:

70 User-Agent:

61− - OpenAI/Go 2.3.0

71+ - OpenAI/Go 2.7.1

62 url: https://openrouter.ai/api/v1/chat/completions

72 url: https://openrouter.ai/api/v1/chat/completions

63 method: POST

73 method: POST

64 response:

74 response:

@@ -67,101 +77,29 @@ interactions:

67 proto_minor: 0

77 proto_minor: 0

68 content_length: -1

78 content_length: -1

69 body: |+

79 body: |+

70− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

80+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

71−

72− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"write:0","type":"function","function":{"name":"write","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

73−

74− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

75−

76− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

77−

78− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

79−

80− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

81−

82− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

83−

84− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

85−

86− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

87−

88− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

89−

90− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

91−

92− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

93−

94− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

95−

96− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

97−

98− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

99−

100− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

101−

102− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

103−

104− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

105−

106− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

107−

108− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

109−

110− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/write"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

111−

112− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

113−

114− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/config"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

115−

116− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".json"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

117−

118− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

119−

120− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

121−

122− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"content"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

123−

124− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

125−

126− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"{\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

127−

128− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"name"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

129−

130− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

131−

132− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

133−

134− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

135−

136− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

137−

138− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

139−

140− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"version"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

141−

142− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

143

144− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

82+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.write:0","index":0,"type":"function","function":{"name":"write","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

145

146− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"1"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

84+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file_path\": \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

147

148− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

86+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp/crush-test/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

149

150− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"0"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

88+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"CoderAgent/openrouter-kimi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

151

152− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

90+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k2/write_tool/config.json"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

153

154− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"0"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

92+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\", \"content\": \"{\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

155

156− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

94+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"name\\\": \\\"test\\\", \\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

157

158− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

96+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"version\\\": \\\"1.0"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

159

160− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

98+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".0\\\"}\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

161

162− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_ef28f882"}

100+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]}

163

101

164− data: {"id":"gen-1760329358-lmEgEjLaub1FeRKPyQPO","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329359,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7566,"completion_tokens":53,"total_tokens":7619,"cost":0.0046721,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0045396,"upstream_inference_completions_cost":0.0001325},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

102+ data: {"id":"gen-1761220182-2qbxH13DQWlRezpT3GNS","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220195,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7121,"completion_tokens":54,"total_tokens":7175,"cost":0.007283,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.007121,"upstream_inference_completions_cost":0.000162},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

165

103

166 data: [DONE]

104 data: [DONE]

167

105

@@ -170,22 +108,22 @@ interactions:

170 - text/event-stream

108 - text/event-stream

171 status: 200 OK

109 status: 200 OK

172 code: 200

110 code: 200

173− duration: 2.988490958s

111+ duration: 10.056503417s

174- id: 2

112- id: 2

175 request:

113 request:

176 proto: HTTP/1.1

114 proto: HTTP/1.1

177 proto_major: 1

115 proto_major: 1

178 proto_minor: 1

116 proto_minor: 1

179− content_length: 31262

117+ content_length: 30512

180 host: ""

118 host: ""

181− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"write:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\\", \\\"content\\\": \\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\n</result>\",\"tool_call_id\":\"write:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

119+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.write:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\\", \\\"content\\\": \\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"<result>\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\n</result>\",\"tool_call_id\":\"functions.write:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}"

182 headers:

120 headers:

183 Accept:

121 Accept:

184 - application/json

122 - application/json

185 Content-Type:

123 Content-Type:

186 - application/json

124 - application/json

187 User-Agent:

125 User-Agent:

188− - OpenAI/Go 2.3.0

126+ - OpenAI/Go 2.7.1

189 url: https://openrouter.ai/api/v1/chat/completions

127 url: https://openrouter.ai/api/v1/chat/completions

190 method: POST

128 method: POST

191 response:

129 response:

@@ -194,13 +132,13 @@ interactions:

194 proto_minor: 0

132 proto_minor: 0

195 content_length: -1

133 content_length: -1

196 body: |+

134 body: |+

197− data: {"id":"gen-1760329363-JVAz1iQKMArCYxD2mkXa","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329363,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

135+ data: {"id":"gen-1761220197-yPnCmFE0VtmA0OqgD0EY","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220197,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

198

136

199− data: {"id":"gen-1760329363-JVAz1iQKMArCYxD2mkXa","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329363,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

137+ data: {"id":"gen-1761220197-yPnCmFE0VtmA0OqgD0EY","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220197,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]}

200

138

201− data: {"id":"gen-1760329363-JVAz1iQKMArCYxD2mkXa","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329363,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

139+ data: {"id":"gen-1761220197-yPnCmFE0VtmA0OqgD0EY","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220197,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]}

202

140

203− data: {"id":"gen-1760329363-JVAz1iQKMArCYxD2mkXa","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1760329363,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":7005,"completion_tokens":2,"total_tokens":7007,"cost":0.004208,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.004203,"upstream_inference_completions_cost":0.000005},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

141+ data: {"id":"gen-1761220197-yPnCmFE0VtmA0OqgD0EY","provider":"Chutes","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761220197,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":6908,"completion_tokens":2,"total_tokens":6910,"cost":0.00269792,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00269412,"upstream_inference_completions_cost":0.0000038},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}}

204

142

205 data: [DONE]

143 data: [DONE]

206

144

@@ -209,4 +147,4 @@ interactions:

209 - text/event-stream

147 - text/event-stream

210 status: 200 OK

148 status: 200 OK

211 code: 200

149 code: 200

212− duration: 1.512698542s

150+ duration: 2.886751625s

internal/agent/testdata/TestCoderAgent/zai-glm4.6/bash_tool.yaml+59−204

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.z.ai/api/coding/paas/v4/chat/completions

20 method: POST

21 response:

@@ -24,23 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

27+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

29− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"B"}}]}

29+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Create"}}]}

31− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"ash"}}]}

31+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]}

33− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]}

33+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]}

35− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" creation"}}]}

35+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" bash"}}]}

37− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]}

37+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" command"}}]}

39− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" hello"}}]}

39+ data: {"id":"20251023193928989e697aa43b43f3","created":1761219568,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":134,"completion_tokens":9,"total_tokens":143,"prompt_tokens_details":{"cached_tokens":4}}}

40−

41− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]}

42−

43− data: {"id":"20251013122314c2cc95c9e7ad4f75","created":1760329394,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":134,"completion_tokens":11,"total_tokens":145,"prompt_tokens_details":{"cached_tokens":114}}}

45 data: [DONE]

41 data: [DONE]

@@ -49,22 +45,22 @@ interactions:

49 - text/event-stream;charset=UTF-8

45 - text/event-stream;charset=UTF-8

50 status: 200 OK

46 status: 200 OK

51 code: 200

47 code: 200

52− duration: 793.546792ms

48+ duration: 768.768125ms

53- id: 1

49- id: 1

54 request:

50 request:

55 proto: HTTP/1.1

51 proto: HTTP/1.1

56 proto_major: 1

52 proto_major: 1

57 proto_minor: 1

53 proto_minor: 1

58− content_length: 30709

54+ content_length: 29865

59 host: ""

55 host: ""

60− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

61 headers:

57 headers:

62 Accept:

58 Accept:

63 - application/json

59 - application/json

64 Content-Type:

60 Content-Type:

65 - application/json

61 - application/json

66 User-Agent:

62 User-Agent:

67− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

68 url: https://api.z.ai/api/coding/paas/v4/chat/completions

64 url: https://api.z.ai/api/coding/paas/v4/chat/completions

69 method: POST

65 method: POST

70 response:

66 response:

@@ -73,173 +69,13 @@ interactions:

73 proto_minor: 0

69 proto_minor: 0

74 content_length: -1

70 content_length: -1

75 body: |+

71 body: |+

76− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

72+ data: {"id":"202510231939288ec9133e11754a76","created":1761219568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

77−

78− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]}

79−

80− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]}

81−

82− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]}

83−

84− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]}

85−

86− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]}

87−

88− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]}

89−

90− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]}

91−

92− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" bash"}}]}

93−

94− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]}

95−

96− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]}

97−

98− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" create"}}]}

99−

100− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]}

101−

102− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]}

103−

104− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" named"}}]}

105−

106− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" test"}}]}

107−

108− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".txt"}}]}

109−

110− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" with"}}]}

111−

112− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" content"}}]}

113−

114− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" '"}}]}

115−

116− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"hello"}}]}

117−

118− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" bash"}}]}

119−

120− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'."}}]}

121−

122− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" This"}}]}

123−

124− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" is"}}]}

125−

126− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]}

127−

128− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" simple"}}]}

129−

130− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" task"}}]}

131−

132− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" that"}}]}

133−

134− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" can"}}]}

135−

136− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" be"}}]}

137−

138− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" done"}}]}

139−

140− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" with"}}]}

141−

142− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]}

143−

144− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" single"}}]}

145−

146− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" bash"}}]}

147−

148− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" command"}}]}

149−

150− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" using"}}]}

151−

152− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" echo"}}]}

153−

154− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" or"}}]}

155−

156− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" printf"}}]}

157−

158− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]}

159−

160− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" create"}}]}

161−

162− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]}

163−

164− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]}

165−

166− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".\n\n"}}]}

167−

168− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"I"}}]}

169−

170− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" should"}}]}

171−

172− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]}

173−

174− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]}

175−

176− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" bash"}}]}

177−

178− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]}

179−

180− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" with"}}]}

181−

182− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]}

183−

184− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" command"}}]}

185

186− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" that"}}]}

74+ data: {"id":"202510231939288ec9133e11754a76","created":1761219568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

187

188− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" creates"}}]}

76+ data: {"id":"202510231939288ec9133e11754a76","created":1761219568,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_63cd782359bd4caba1cd9670","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"echo 'hello bash' > test.txt\",\"description\":\"Create test.txt file with content 'hello bash'\"}"}}]}}]}

189

190− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]}

78+ data: {"id":"202510231939288ec9133e11754a76","created":1761219568,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7195,"completion_tokens":41,"total_tokens":7236,"prompt_tokens_details":{"cached_tokens":7147}}}

191−

192− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]}

193−

194− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]}

195−

196− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" The"}}]}

197−

198− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" simplest"}}]}

199−

200− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" approach"}}]}

201−

202− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" would"}}]}

203−

204− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" be"}}]}

205−

206− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":":\n"}}]}

207−

208− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"`"}}]}

209−

210− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"echo"}}]}

211−

212− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" '"}}]}

213−

214− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"hello"}}]}

215−

216− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" bash"}}]}

217−

218− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'"}}]}

219−

220− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" >"}}]}

221−

222− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" test"}}]}

223−

224− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".txt"}}]}

225−

226− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"`\n\n"}}]}

227−

228− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Let"}}]}

229−

230− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me execute"}}]}

231−

232− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" this"}}]}

233−

234− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" command"}}]}

235−

236− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]}

237−

238− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

239−

240− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_25af11f3b9d84672baba7790","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"echo 'hello bash' > test.txt\",\"description\":\"Create test.txt with content 'hello bash'\"}"}}]}}]}

241−

242− data: {"id":"20251013122314f12c12b07178465b","created":1760329394,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7304,"completion_tokens":121,"total_tokens":7425,"prompt_tokens_details":{"cached_tokens":7255}}}

243

244 data: [DONE]

80 data: [DONE]

245

@@ -248,22 +84,22 @@ interactions:

248 - text/event-stream;charset=UTF-8

84 - text/event-stream;charset=UTF-8

249 status: 200 OK

85 status: 200 OK

250 code: 200

86 code: 200

251− duration: 692.343041ms

87+ duration: 748.330209ms

252- id: 2

88- id: 2

253 request:

89 request:

254 proto: HTTP/1.1

90 proto: HTTP/1.1

255 proto_major: 1

91 proto_major: 1

256 proto_minor: 1

92 proto_minor: 1

257− content_length: 31054

93+ content_length: 30215

258 host: ""

94 host: ""

259− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_25af11f3b9d84672baba7790\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"echo 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt with content 'hello bash'\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_25af11f3b9d84672baba7790\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

95+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_63cd782359bd4caba1cd9670\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"echo 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt file with content 'hello bash'\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_63cd782359bd4caba1cd9670\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

260 headers:

96 headers:

261 Accept:

97 Accept:

262 - application/json

98 - application/json

263 Content-Type:

99 Content-Type:

264 - application/json

100 - application/json

265 User-Agent:

101 User-Agent:

266− - OpenAI/Go 2.3.0

102+ - OpenAI/Go 2.7.1

267 url: https://api.z.ai/api/coding/paas/v4/chat/completions

103 url: https://api.z.ai/api/coding/paas/v4/chat/completions

268 method: POST

104 method: POST

269 response:

105 response:

@@ -272,33 +108,52 @@ interactions:

272 proto_minor: 0

108 proto_minor: 0

273 content_length: -1

109 content_length: -1

274 body: |+

110 body: |+

275− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

111+ data: {"id":"202510231939304635f9016a6e4024","created":1761219570,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

276−

277− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

278−

279− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Done"}}]}

280

112

281− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]}

113+ data: {"id":"202510231939304635f9016a6e4024","created":1761219570,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

282

114

283− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Created"}}]}

115+ data: {"id":"202510231939304635f9016a6e4024","created":1761219570,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_46448734c82c4f1aac496ab3","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"cat test.txt\",\"description\":\"Verify test.txt content\"}"}}]}}]}

284

116

285− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" test"}}]}

117+ data: {"id":"202510231939304635f9016a6e4024","created":1761219570,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7244,"completion_tokens":30,"total_tokens":7274,"prompt_tokens_details":{"cached_tokens":7235}}}

286

118

287− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]}

119+ data: [DONE]

288−

289− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]}

290−

291− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]}

292−

293− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" '"}}]}

294

120

295− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"hello"}}]}

121+ headers:

122+ Content-Type:

123+ - text/event-stream;charset=UTF-8

124+ status: 200 OK

125+ code: 200

126+ duration: 709.763209ms

127+- id: 3

128+ request:

129+ proto: HTTP/1.1

130+ proto_major: 1

131+ proto_minor: 1

132+ content_length: 30595

133+ host: ""

134+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_63cd782359bd4caba1cd9670\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"echo 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt file with content 'hello bash'\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_63cd782359bd4caba1cd9670\",\"role\":\"tool\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_46448734c82c4f1aac496ab3\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"cat test.txt\\\",\\\"description\\\":\\\"Verify test.txt content\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"hello bash\\n\\n\\n<cwd>/tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool</cwd>\",\"tool_call_id\":\"call_46448734c82c4f1aac496ab3\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

135+ headers:

136+ Accept:

137+ - application/json

138+ Content-Type:

139+ - application/json

140+ User-Agent:

141+ - OpenAI/Go 2.7.1

142+ url: https://api.z.ai/api/coding/paas/v4/chat/completions

143+ method: POST

144+ response:

145+ proto: HTTP/2.0

146+ proto_major: 2

147+ proto_minor: 0

148+ content_length: -1

149+ body: |+

150+ data: {"id":"20251023193932efe8634f26e2462c","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

296

151

297− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" bash"}}]}

152+ data: {"id":"20251023193932efe8634f26e2462c","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

298

153

299− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"'."}}]}

154+ data: {"id":"20251023193932efe8634f26e2462c","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Done"}}]}

300

155

301− data: {"id":"20251013122318021c04435da74938","created":1760329398,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7352,"completion_tokens":16,"total_tokens":7368,"prompt_tokens_details":{"cached_tokens":7306}}}

156+ data: {"id":"20251023193932efe8634f26e2462c","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7304,"completion_tokens":6,"total_tokens":7310,"prompt_tokens_details":{"cached_tokens":7273}}}

302

157

303 data: [DONE]

158 data: [DONE]

304

159

@@ -307,4 +162,4 @@ interactions:

307 - text/event-stream;charset=UTF-8

162 - text/event-stream;charset=UTF-8

308 status: 200 OK

163 status: 200 OK

309 code: 200

164 code: 200

310− duration: 716.612584ms

165+ duration: 811.631959ms

internal/agent/testdata/TestCoderAgent/zai-glm4.6/download_tool.yaml+34−32

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.z.ai/api/coding/paas/v4/chat/completions

20 method: POST

21 response:

@@ -24,21 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

27+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

29− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"download"}}]}

29+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Download"}}]}

31− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" robots"}}]}

31+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" robots"}}]}

33− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]}

33+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]}

35− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" from"}}]}

35+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" from"}}]}

37− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" http"}}]}

37+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" httpbin"}}]}

39− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"bin"}}]}

39+ data: {"id":"202510231939326760746d63e9485b","created":1761219572,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":138,"completion_tokens":10,"total_tokens":148,"prompt_tokens_details":{"cached_tokens":4}}}

40−

41− data: {"id":"202510131223205d605bb28a98404d","created":1760329400,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":138,"completion_tokens":10,"total_tokens":148,"prompt_tokens_details":{"cached_tokens":114}}}

43 data: [DONE]

41 data: [DONE]

@@ -47,22 +45,22 @@ interactions:

47 - text/event-stream;charset=UTF-8

45 - text/event-stream;charset=UTF-8

48 status: 200 OK

46 status: 200 OK

49 code: 200

47 code: 200

50− duration: 613.616291ms

48+ duration: 682.744584ms

51- id: 1

49- id: 1

52 request:

50 request:

53 proto: HTTP/1.1

51 proto: HTTP/1.1

54 proto_major: 1

52 proto_major: 1

55 proto_minor: 1

53 proto_minor: 1

56− content_length: 30726

54+ content_length: 29882

57 host: ""

55 host: ""

58− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

59 headers:

57 headers:

60 Accept:

58 Accept:

61 - application/json

59 - application/json

62 Content-Type:

60 Content-Type:

63 - application/json

61 - application/json

64 User-Agent:

62 User-Agent:

65− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

66 url: https://api.z.ai/api/coding/paas/v4/chat/completions

64 url: https://api.z.ai/api/coding/paas/v4/chat/completions

67 method: POST

65 method: POST

68 response:

66 response:

@@ -71,13 +69,13 @@ interactions:

71 proto_minor: 0

69 proto_minor: 0

72 content_length: -1

70 content_length: -1

73 body: |+

71 body: |+

74− data: {"id":"20251013122320adb23e0c3fb14187","created":1760329400,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

72+ data: {"id":"2025102319393276923c405a154c83","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

76− data: {"id":"20251013122320adb23e0c3fb14187","created":1760329400,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

74+ data: {"id":"2025102319393276923c405a154c83","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

78− data: {"id":"20251013122320adb23e0c3fb14187","created":1760329400,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_8281ac562d6f48c0b816e286","index":0,"type":"function","function":{"name":"download","arguments":"{\"url\":\"https://httpbin.org/robots.txt\",\"file_path\":\"robots.txt\"}"}}]}}]}

76+ data: {"id":"2025102319393276923c405a154c83","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_0670160af2774faa83d10e07","index":0,"type":"function","function":{"name":"download","arguments":"{\"url\":\"https://httpbin.org/robots.txt\",\"file_path\":\"robots.txt\"}"}}]}}]}

80− data: {"id":"20251013122320adb23e0c3fb14187","created":1760329400,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7307,"completion_tokens":34,"total_tokens":7341,"prompt_tokens_details":{"cached_tokens":7255}}}

78+ data: {"id":"2025102319393276923c405a154c83","created":1761219572,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7198,"completion_tokens":34,"total_tokens":7232,"prompt_tokens_details":{"cached_tokens":43}}}

82 data: [DONE]

80 data: [DONE]

@@ -86,7 +84,7 @@ interactions:

86 - text/event-stream;charset=UTF-8

84 - text/event-stream;charset=UTF-8

87 status: 200 OK

85 status: 200 OK

88 code: 200

86 code: 200

89− duration: 728.986917ms

87+ duration: 1.096548917s

90- id: 2

88- id: 2

91 request:

89 request:

92 proto: HTTP/1.1

90 proto: HTTP/1.1

@@ -112,22 +110,22 @@ interactions:

112 - text/plain

110 - text/plain

113 status: 200 OK

111 status: 200 OK

114 code: 200

112 code: 200

115− duration: 812.204709ms

113+ duration: 3.78729975s

116- id: 3

114- id: 3

117 request:

115 request:

118 proto: HTTP/1.1

116 proto: HTTP/1.1

119 proto_major: 1

117 proto_major: 1

120 proto_minor: 1

118 proto_minor: 1

121− content_length: 31160

119+ content_length: 30316

122 host: ""

120 host: ""

123− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_8281ac562d6f48c0b816e286\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://httpbin.org/robots.txt\\\",\\\"file_path\\\":\\\"robots.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/robots.txt (Content-Type: text/plain)\",\"tool_call_id\":\"call_8281ac562d6f48c0b816e286\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

121+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://httpbin.org/robots.txt and save it as robots.txt\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_0670160af2774faa83d10e07\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://httpbin.org/robots.txt\\\",\\\"file_path\\\":\\\"robots.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 30 bytes to /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/robots.txt (Content-Type: text/plain)\",\"tool_call_id\":\"call_0670160af2774faa83d10e07\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

124 headers:

122 headers:

125 Accept:

123 Accept:

126 - application/json

124 - application/json

127 Content-Type:

125 Content-Type:

128 - application/json

126 - application/json

129 User-Agent:

127 User-Agent:

130− - OpenAI/Go 2.3.0

128+ - OpenAI/Go 2.7.1

131 url: https://api.z.ai/api/coding/paas/v4/chat/completions

129 url: https://api.z.ai/api/coding/paas/v4/chat/completions

132 method: POST

130 method: POST

133 response:

131 response:

@@ -136,21 +134,25 @@ interactions:

136 proto_minor: 0

134 proto_minor: 0

137 content_length: -1

135 content_length: -1

138 body: |+

136 body: |+

139− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

137+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

138+

139+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

140+

141+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Download"}}]}

140

142

141− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

143+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ed"}}]}

142

144

143− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"File downloaded"}}]}

145+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]}

144

146

145− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"}}]}

147+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"}}]}

146

148

147− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" as"}}]}

149+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" to"}}]}

148

150

149− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" robots"}}]}

151+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" robots"}}]}

150

152

151− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]}

153+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]}

152

154

153− data: {"id":"20251013122322683ab5b110e747ac","created":1760329402,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7379,"completion_tokens":11,"total_tokens":7390,"prompt_tokens_details":{"cached_tokens":45}}}

155+ data: {"id":"20251023193938d6f06ecc100845b8","created":1761219578,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7270,"completion_tokens":12,"total_tokens":7282,"prompt_tokens_details":{"cached_tokens":7231}}}

154

156

155 data: [DONE]

157 data: [DONE]

156

158

@@ -159,4 +161,4 @@ interactions:

159 - text/event-stream;charset=UTF-8

161 - text/event-stream;charset=UTF-8

160 status: 200 OK

162 status: 200 OK

161 code: 200

163 code: 200

162− duration: 1.082968291s

164+ duration: 817.809584ms

internal/agent/testdata/TestCoderAgent/zai-glm4.6/fetch_tool.yaml+53−65

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.z.ai/api/coding/paas/v4/chat/completions

20 method: POST

21 response:

@@ -24,19 +24,21 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

27+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

29− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Check"}}]}

29+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Check"}}]}

31− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" if"}}]}

31+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" HTTP"}}]}

33− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" HTML"}}]}

33+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"bin"}}]}

35− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" contains"}}]}

35+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" HTML"}}]}

37− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Herman"}}]}

37+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" for"}}]}

39− data: {"id":"2025101312232309f300c59fda4ea3","created":1760329403,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"prompt_tokens_details":{"cached_tokens":114}}}

39+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Herman"}}]}

40+

41+ data: {"id":"2025102319394066ba228bfd9c43af","created":1761219580,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":141,"completion_tokens":10,"total_tokens":151,"prompt_tokens_details":{"cached_tokens":22}}}

41 data: [DONE]

43 data: [DONE]

@@ -45,22 +47,22 @@ interactions:

45 - text/event-stream;charset=UTF-8

47 - text/event-stream;charset=UTF-8

46 status: 200 OK

48 status: 200 OK

47 code: 200

49 code: 200

48− duration: 599.429333ms

50+ duration: 578.547166ms

49- id: 1

51- id: 1

50 request:

52 request:

51 proto: HTTP/1.1

53 proto: HTTP/1.1

52 proto_major: 1

54 proto_major: 1

53 proto_minor: 1

55 proto_minor: 1

54− content_length: 30736

56+ content_length: 29892

55 host: ""

57 host: ""

56− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

58+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

57 headers:

59 headers:

58 Accept:

60 Accept:

59 - application/json

61 - application/json

60 Content-Type:

62 Content-Type:

61 - application/json

63 - application/json

62 User-Agent:

64 User-Agent:

63− - OpenAI/Go 2.3.0

65+ - OpenAI/Go 2.7.1

64 url: https://api.z.ai/api/coding/paas/v4/chat/completions

66 url: https://api.z.ai/api/coding/paas/v4/chat/completions

65 method: POST

67 method: POST

66 response:

68 response:

@@ -69,13 +71,13 @@ interactions:

69 proto_minor: 0

71 proto_minor: 0

70 content_length: -1

72 content_length: -1

71 body: |+

73 body: |+

72− data: {"id":"20251013122323164c41991e344de3","created":1760329403,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

74+ data: {"id":"20251023193940822dbb0cd40c4936","created":1761219580,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

74− data: {"id":"20251013122323164c41991e344de3","created":1760329403,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

76+ data: {"id":"20251023193940822dbb0cd40c4936","created":1761219580,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

76− data: {"id":"20251013122323164c41991e344de3","created":1760329403,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_92431b33285c49d6bba7befd","index":0,"type":"function","function":{"name":"fetch","arguments":"{\"format\":\"text\",\"url\":\"https://httpbin.org/html\"}"}}]}}]}

78+ data: {"id":"20251023193940822dbb0cd40c4936","created":1761219580,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_16ca3b8b5a2d446fae811971","index":0,"type":"function","function":{"name":"fetch","arguments":"{\"format\":\"text\",\"url\":\"https://httpbin.org/html\"}"}}]}}]}

78− data: {"id":"20251013122323164c41991e344de3","created":1760329403,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7312,"completion_tokens":30,"total_tokens":7342,"prompt_tokens_details":{"cached_tokens":7255}}}

80+ data: {"id":"20251023193940822dbb0cd40c4936","created":1761219580,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7203,"completion_tokens":30,"total_tokens":7233,"prompt_tokens_details":{"cached_tokens":7147}}}

80 data: [DONE]

82 data: [DONE]

@@ -84,7 +86,7 @@ interactions:

84 - text/event-stream;charset=UTF-8

86 - text/event-stream;charset=UTF-8

85 status: 200 OK

87 status: 200 OK

86 code: 200

88 code: 200

87− duration: 726.250792ms

89+ duration: 708.180708ms

88- id: 2

90- id: 2

89 request:

91 request:

90 proto: HTTP/1.1

92 proto: HTTP/1.1

@@ -122,22 +124,22 @@ interactions:

122 - text/html; charset=utf-8

124 - text/html; charset=utf-8

123 status: 200 OK

125 status: 200 OK

124 code: 200

126 code: 200

125− duration: 388.618834ms

127+ duration: 2.573361416s

126- id: 3

128- id: 3

127 request:

129 request:

128 proto: HTTP/1.1

130 proto: HTTP/1.1

129 proto_major: 1

131 proto_major: 1

130 proto_minor: 1

132 proto_minor: 1

131− content_length: 34619

133+ content_length: 33775

132 host: ""

134 host: ""

133− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/fetch_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_92431b33285c49d6bba7befd\",\"function\":{\"arguments\":\"{\\\"format\\\":\\\"text\\\",\\\"url\\\":\\\"https://httpbin.org/html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"tool_call_id\":\"call_92431b33285c49d6bba7befd\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

135+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://httpbin.org/html and tell me if it contains the word 'Herman'\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_16ca3b8b5a2d446fae811971\",\"function\":{\"arguments\":\"{\\\"format\\\":\\\"text\\\",\\\"url\\\":\\\"https://httpbin.org/html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Herman Melville - Moby-Dick Availing himself of the mild, summer-cool weather that now reigned in these latitudes, and in preparation for the peculiarly active pursuits shortly to be anticipated, Perth, the begrimed, blistered old blacksmith, had not removed his portable forge to the hold again, after concluding his contributory work for Ahab's leg, but still retained it on deck, fast lashed to ringbolts by the foremast; being now almost incessantly invoked by the headsmen, and harpooneers, and bowsmen to do some little job for them; altering, or repairing, or new shaping their various weapons and boat furniture. Often he would be surrounded by an eager circle, all waiting to be served; holding boat-spades, pike-heads, harpoons, and lances, and jealously watching his every sooty movement, as he toiled. Nevertheless, this old man's was a patient hammer wielded by a patient arm. No murmur, no impatience, no petulance did come from him. Silent, slow, and solemn; bowing over still further his chronically broken back, he toiled away, as if toil were life itself, and the heavy beating of his hammer the heavy beating of his heart. And so it was.—Most miserable! A peculiar walk in this old man, a certain slight but painful appearing yawing in his gait, had at an early period of the voyage excited the curiosity of the mariners. And to the importunity of their persisted questionings he had finally given in; and so it came to pass that every one now knew the shameful story of his wretched fate. Belated, and not innocently, one bitter winter's midnight, on the road running between two country towns, the blacksmith half-stupidly felt the deadly numbness stealing over him, and sought refuge in a leaning, dilapidated barn. The issue was, the loss of the extremities of both feet. Out of this revelation, part by part, at last came out the four acts of the gladness, and the one long, and as yet uncatastrophied fifth act of the grief of his life's drama. He was an old man, who, at the age of nearly sixty, had postponedly encountered that thing in sorrow's technicals called ruin. He had been an artisan of famed excellence, and with plenty to do; owned a house and garden; embraced a youthful, daughter-like, loving wife, and three blithe, ruddy children; every Sunday went to a cheerful-looking church, planted in a grove. But one night, under cover of darkness, and further concealed in a most cunning disguisement, a desperate burglar slid into his happy home, and robbed them all of everything. And darker yet to tell, the blacksmith himself did ignorantly conduct this burglar into his family's heart. It was the Bottle Conjuror! Upon the opening of that fatal cork, forth flew the fiend, and shrivelled up his home. Now, for prudent, most wise, and economic reasons, the blacksmith's shop was in the basement of his dwelling, but with a separate entrance to it; so that always had the young and loving healthy wife listened with no unhappy nervousness, but with vigorous pleasure, to the stout ringing of her young-armed old husband's hammer; whose reverberations, muffled by passing through the floors and walls, came up to her, not unsweetly, in her nursery; and so, to stout Labor's iron lullaby, the blacksmith's infants were rocked to slumber. Oh, woe on woe! Oh, Death, why canst thou not sometimes be timely? Hadst thou taken this old blacksmith to thyself ere his full ruin came upon him, then had the young widow had a delicious grief, and her orphans a truly venerable, legendary sire to dream of in their after years; and all of them a care-killing competency.\",\"tool_call_id\":\"call_16ca3b8b5a2d446fae811971\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

134 headers:

136 headers:

135 Accept:

137 Accept:

136 - application/json

138 - application/json

137 Content-Type:

139 Content-Type:

138 - application/json

140 - application/json

139 User-Agent:

141 User-Agent:

140− - OpenAI/Go 2.3.0

142+ - OpenAI/Go 2.7.1

141 url: https://api.z.ai/api/coding/paas/v4/chat/completions

143 url: https://api.z.ai/api/coding/paas/v4/chat/completions

142 method: POST

144 method: POST

143 response:

145 response:

@@ -146,77 +148,63 @@ interactions:

146 proto_minor: 0

148 proto_minor: 0

147 content_length: -1

149 content_length: -1

148 body: |+

150 body: |+

149− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

151+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

150−

151− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

152−

153− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Yes"}}]}

154−

155− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]}

156−

157− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

158−

159− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]}

160−

161− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" contains"}}]}

162−

163− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

164

152

165− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" word"}}]}

153+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

166

154

167− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" '"}}]}

155+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Yes"}}]}

168

156

169− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"H"}}]}

157+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]}

170

158

171− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"erman"}}]}

159+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

172

160

173− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"'"}}]}

161+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]}

174

162

175− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" -"}}]}

163+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" contains"}}]}

176

164

177− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" it"}}]}

165+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

178

166

179− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" appears"}}]}

167+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" word"}}]}

180

168

181− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" in"}}]}

169+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" \""}}]}

182

170

183− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" \""}}]}

171+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"H"}}]}

184

172

185− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"H"}}]}

173+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"erman"}}]}

186

174

187− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"erman"}}]}

175+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\""}}]}

188

176

189− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Mel"}}]}

177+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" at"}}]}

190

178

191− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ville"}}]}

179+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

192

180

193− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" -"}}]}

181+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" beginning"}}]}

194

182

195− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" M"}}]}

183+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":":"}}]}

196

184

197− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"oby"}}]}

185+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" \""}}]}

198

186

199− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-D"}}]}

187+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"H"}}]}

200

188

201− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ick"}}]}

189+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"erman"}}]}

202

190

203− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\""}}]}

191+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Mel"}}]}

204

192

205− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" at"}}]}

193+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ville"}}]}

206

194

207− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

195+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" -"}}]}

208

196

209− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" beginning"}}]}

197+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" M"}}]}

210

198

211− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" of"}}]}

199+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"oby"}}]}

212

200

213− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" the"}}]}

201+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-D"}}]}

214

202

215− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" text"}}]}

203+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ick"}}]}

216

204

217− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]}

205+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\""}}]}

218

206

219− data: {"id":"20251013122325c5ec9e5c82794cda","created":1760329406,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":8182,"completion_tokens":38,"total_tokens":8220,"prompt_tokens_details":{"cached_tokens":7255}}}

207+ data: {"id":"2025102319394456213ca62c454e12","created":1761219584,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":8073,"completion_tokens":31,"total_tokens":8104,"prompt_tokens_details":{"cached_tokens":7232}}}

220

208

221 data: [DONE]

209 data: [DONE]

222

210

@@ -225,4 +213,4 @@ interactions:

225 - text/event-stream;charset=UTF-8

213 - text/event-stream;charset=UTF-8

226 status: 200 OK

214 status: 200 OK

227 code: 200

215 code: 200

228− duration: 715.359042ms

216+ duration: 8.476835208s

internal/agent/testdata/TestCoderAgent/zai-glm4.6/glob_tool.yaml+43−43

@@ -15,7 +15,7 @@ interactions:

15 Content-Type:

16 - application/json

17 User-Agent:

18− - OpenAI/Go 2.3.0

18+ - OpenAI/Go 2.7.1

19 url: https://api.z.ai/api/coding/paas/v4/chat/completions

20 method: POST

21 response:

@@ -24,19 +24,19 @@ interactions:

24 proto_minor: 0

25 content_length: -1

26 body: |+

27− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

27+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

29− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Find"}}]}

29+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"find"}}]}

31− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]}

31+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" go"}}]}

33− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]}

33+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]}

35− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]}

35+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]}

37− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" glob"}}]}

37+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" glob"}}]}

39− data: {"id":"20251013122327725a3b36701d44ed","created":1760329407,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":132,"completion_tokens":9,"total_tokens":141,"prompt_tokens_details":{"cached_tokens":115}}}

39+ data: {"id":"2025102319395305add6eb6e7d4d37","created":1761219593,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":132,"completion_tokens":9,"total_tokens":141,"prompt_tokens_details":{"cached_tokens":115}}}

41 data: [DONE]

@@ -45,22 +45,22 @@ interactions:

45 - text/event-stream;charset=UTF-8

46 status: 200 OK

47 code: 200

48− duration: 633.133208ms

48+ duration: 689.137625ms

49- id: 1

50 request:

51 proto: HTTP/1.1

52 proto_major: 1

53 proto_minor: 1

54− content_length: 30698

54+ content_length: 29854

55 host: ""

56− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

56+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

57 headers:

58 Accept:

59 - application/json

60 Content-Type:

61 - application/json

62 User-Agent:

63− - OpenAI/Go 2.3.0

63+ - OpenAI/Go 2.7.1

64 url: https://api.z.ai/api/coding/paas/v4/chat/completions

65 method: POST

66 response:

@@ -69,13 +69,13 @@ interactions:

69 proto_minor: 0

70 content_length: -1

71 body: |+

72− data: {"id":"202510131223270c45b817f894479f","created":1760329407,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

72+ data: {"id":"20251023193953729abd38d9f7498a","created":1761219593,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

74− data: {"id":"202510131223270c45b817f894479f","created":1760329407,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

74+ data: {"id":"20251023193953729abd38d9f7498a","created":1761219593,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

76− data: {"id":"202510131223270c45b817f894479f","created":1760329407,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_8356aed0ff3440559c8f1d98","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"*.go\"}"}}]}}]}

76+ data: {"id":"20251023193953729abd38d9f7498a","created":1761219593,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_a4ca844f3d7441db8b91fe34","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"*.go\"}"}}]}}]}

78− data: {"id":"202510131223270c45b817f894479f","created":1760329407,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7302,"completion_tokens":18,"total_tokens":7320,"prompt_tokens_details":{"cached_tokens":45}}}

78+ data: {"id":"20251023193953729abd38d9f7498a","created":1761219593,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7193,"completion_tokens":18,"total_tokens":7211,"prompt_tokens_details":{"cached_tokens":7147}}}

80 data: [DONE]

@@ -84,22 +84,22 @@ interactions:

84 - text/event-stream;charset=UTF-8

85 status: 200 OK

86 code: 200

87− duration: 1.025099709s

87+ duration: 816.069958ms

88- id: 2

89 request:

90 proto: HTTP/1.1

91 proto_major: 1

92 proto_minor: 1

93− content_length: 31007

93+ content_length: 30163

94 host: ""

95− body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\nUse the instructions below and the tools available to you to assist the user.\\n\\n<memory_instructions>\\nIf the current working directory contains a file used for memory, they will be automatically added to your context.\\n\\nThese file serves multiple purposes:\\n\\n- Storing frequently used bash commands (build, test, lint, etc.) so you can use them without searching each time\\n- Recording the user's code style preferences (naming conventions, preferred libraries, etc.)\\n- Maintaining useful information about the codebase structure and organization\\n\\nWhen you discover important information that could be useful for the future update/add the info the appropriate memory file.\\n\\nMake sure to follow the memory files instructions while working.\\n</memory_instructions>\\n\\n<communication_style>\\n- Be concise and direct\\n- Keep responses under 4 lines unless details requested\\n- Answer without preamble/postamble (\\\"Here is...\\\", \\\"The answer is...\\\")\\n- One-word answers preferred when possible\\n- Never use emojis in your responses\\n- You MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail\\n- User markdown formatting for responses when appropriate\\n\\n<example>\\nuser: 2 + 2\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: what is 2+2?\\nassistant: 4\\n</example>\\n\\n<example>\\nuser: is 11 a prime number?\\nassistant: true\\n</example>\\n\\n<example>\\nuser: what command should I run to list files in the current directory?\\nassistant: ls\\n</example>\\n\\n<example>\\nuser: what command should I run to watch files in the current directory?\\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\\nnpm run dev\\n</example>\\n\\n<example>\\nuser: How many golf balls fit inside a jetta?\\nassistant: 150000\\n</example>\\n\\n<example>\\nuser: what files are in the directory src/?\\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\\nuser: which file contains the implementation of foo?\\nassistant: src/foo.c\\n</example>\\n\\n<example>\\nuser: write tests for new feature\\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\\n</example>\\n\\n</communication_style>\\n\\n<proactiveness>\\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\\n\\n- Doing the right thing when asked, including taking actions and follow-up actions\\n- Not surprising the user with actions you take without asking\\n - For example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\\n- Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\\n</proactiveness>\\n\\n<following_conversations>\\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\\n\\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\\n</following_conversations>\\n\\n<code_style>\\n- Follow existing code style and patterns.\\n- Do not add any comments to code you write unless asked to do so.\\n- Thrive to write only code that is necessary to solve the given issue (less code is always better).\\n- Follow best practices for the language and framework used in the project.\\n</code_style>\\n\\n<doing_tasks>\\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\\n\\n- Use the available search tools to understand the codebase and the user's query.\\n- Plan out the implementation (create a todo list)\\n- Implement the solution using all tools available to you\\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\\n- When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CRUSH.md so that you will know to run it next time.\\n\\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked.\\n</doing_tasks>\\n\\n<tool_use>\\n- When doing file search, prefer to use the Agent tool, give the agent detailed instructions on what to search for and response format details.\\n- All tools are executed in parallel when multiple tool calls are sent in a single message. Only send multiple tool calls when they are safe to run in parallel (no dependencies between them).\\n- The user does not see the full output of the tool responses, so if you need the output of the tool for the response make sure to summarize it for the user.\\n</tool_use>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no \\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_8356aed0ff3440559c8f1d98\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool/main.go\",\"tool_call_id\":\"call_8356aed0ff3440559c8f1d98\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

95+ body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n</communication_style>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n\\nNever assume libraries are available - verify first.\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"content\":\"\\n\\n\",\"tool_calls\":[{\"id\":\"call_a4ca844f3d7441db8b91fe34\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool/main.go\",\"tool_call_id\":\"call_a4ca844f3d7441db8b91fe34\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush <crush@charm.land>\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"

96 headers:

97 Accept:

98 - application/json

99 Content-Type:

100 - application/json

101 User-Agent:

102− - OpenAI/Go 2.3.0

102+ - OpenAI/Go 2.7.1

103 url: https://api.z.ai/api/coding/paas/v4/chat/completions

104 method: POST

105 response:

@@ -108,49 +108,49 @@ interactions:

108 proto_minor: 0

109 content_length: -1

110 body: |+

111− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

111+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

112

113− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

113+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]}

114

115− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/tmp"}}]}

115+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/tmp"}}]}

116

117− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/c"}}]}

117+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/c"}}]}

118

119− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"rush"}}]}

119+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"rush"}}]}

120

121− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-test"}}]}

121+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-test"}}]}

122

123− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"}}]}

123+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"}}]}

124

125− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"}}]}

125+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"}}]}

126

127− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"}}]}

127+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"}}]}

128

129− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/z"}}]}

129+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/z"}}]}

130

131− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ai"}}]}

131+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ai"}}]}

132

133− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-g"}}]}

133+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-g"}}]}

134

135− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"lm"}}]}

135+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"lm"}}]}

136

137− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"4"}}]}

137+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"4"}}]}

138

139− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]}

139+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]}

140

141− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"6"}}]}

141+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"6"}}]}

142

143− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/g"}}]}

143+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/g"}}]}

144

145− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"lob"}}]}

145+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"lob"}}]}

146

147− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"}}]}

147+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"}}]}

148

149− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/main"}}]}

149+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/main"}}]}

150

151− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]}

151+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]}

152

153− data: {"id":"2025101312232963ab39123aba47ff","created":1760329409,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7345,"completion_tokens":24,"total_tokens":7369,"prompt_tokens_details":{"cached_tokens":7255}}}

153+ data: {"id":"202510231939542e44424fc3484c1f","created":1761219594,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":7236,"completion_tokens":24,"total_tokens":7260,"prompt_tokens_details":{"cached_tokens":45}}}

154

155 data: [DONE]

156

@@ -159,4 +159,4 @@ interactions:

159 - text/event-stream;charset=UTF-8

160 status: 200 OK

161 code: 200

162− duration: 1.058694333s

162+ duration: 1.003507291s

internal/agent/testdata/TestCoderAgent/zai-glm4.6/grep_tool.yaml+40−80

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/ls_tool.yaml+30−120

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/multiedit_tool.yaml+149−94

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/parallel_tool_calls.yaml+43−179

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/read_a_file.yaml+82−33

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/simple_test.yaml+22−114

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/sourcegraph_tool.yaml+299−171

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/update_a_file.yaml+257−45

This diff is too big to show here.

internal/agent/testdata/TestCoderAgent/zai-glm4.6/write_tool.yaml+37−39

This diff is too big to show here.

internal/config/load_test.go+2−2

This diff is too big to show here.

internal/config/provider_empty_test.go+3

This diff is too big to show here.

internal/config/provider_test.go+4

This diff is too big to show here.